Proactive AMCP

· v1.0.8

High Risk

Proactive immortal — behavior ontology (learn remember stuck) hooks kick in · IPFS soul · Solvr · self-heals on boot · disk check · watchdog 🏴‍☠️

H:4 D:4 A:3 C:1

⚠️ Hazard Flags

EXEC PRIVILEGED PERSISTENCE FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER FS_DELETE NET_EGRESS_ANY CREDS_ENV CREDS_FILES CREDS_KEYCHAIN ACT_SEND_MESSAGE PI_WEB PI_DOCUMENTS

📋 Capabilities

Execution

✅ Shell execution
❌ Code execution
❌ Install dependencies
✅ Persistence
Privilege: admin

Filesystem

✅ Read workspace
✅ Write workspace
✅ Read home
✅ Write home
❌ Read system
✅ Delete

Network

Egress: any
❌ Ingress

Credentials

✅ Environment vars
✅ Credential files
❌ Browser data
✅ Keychain

Actions

✅ send messages❌ post public❌ purchase❌ transfer money❌ deploy❌ delete external

🔒 Containment

Level: maximum

Required:

APPROVE_SEND: Can send messages
SANDBOX_CONTAINER: Code execution capability

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Pipe-to-shell pattern detected (curl|bash) in: scripts/install.sh critical

Mitigation: Do not execute. Review source for malicious intent.

Keychain/credential store access in: scripts/_checkpoint-full.sh high

Mitigation: Block keychain access or use isolated environment.

Unauthorized tool use: TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_CRITICAL_ACCESS, MCP_SYS_PROCESS_MANIPULATION, INSTRUCTED_GIT_CLONE_AND_BUILD critical

Mitigation: Remove system modification commands

Command injection risk: COMMAND_INJECTION_USER_INPUT, COMMAND_INJECTION_EVAL critical

Mitigation: Validate and sanitize all user inputs before using in commands

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low

Mitigation: Provide clear, detailed description of skill functionality

Data exfiltration patterns: DATA_EXFIL_SENSITIVE_FILES, DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS high

Mitigation: Do not access credential files or sensitive system files

Want a deeper analysis?

This report was generated by static analysis. Get an LLM-powered deep review with behavioral reasoning and attack surface mapping.

🧠 Deep Analysis — $5.00

🚨 Incident Response

Kill switch: Stop the agent process

Containment: Review logs for unexpected actions

Recovery: Depends on skill capabilities

📄 Raw SSDS JSON click to expand

{
  "meta": {
    "document_id": "ssds:auto:proactive-amcp:1.0.8",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T13:45:30.902Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Proactive AMCP",
    "version": "1.0.8",
    "format": "agent_skill",
    "description": "Proactive immortal — behavior ontology (learn remember stuck) hooks kick in · IPFS soul · Solvr · self-heals on boot · disk check · watchdog 🏴‍☠️",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "b6672f88d3451e2a42d19dffa9d41156fb68bad4496db2ea37c08d42b434728b",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": false,
      "privilege_level": "admin",
      "can_install_deps": false,
      "can_persist": true
    },
    "filesystem": {
      "reads_workspace": true,
      "reads_user_home": true,
      "reads_system": false,
      "writes_workspace": true,
      "writes_user_home": true,
      "writes_system": false,
      "can_delete": true
    },
    "network": {
      "egress": "any",
      "ingress": false
    },
    "credentials": {
      "reads_env_vars": true,
      "reads_credential_files": true,
      "reads_browser_data": false,
      "reads_keychain": true
    },
    "services": [
      {
        "service": "messaging",
        "operations": [
          "read",
          "write"
        ]
      }
    ],
    "actions": {
      "can_send_messages": true,
      "can_post_public": false,
      "can_purchase": false,
      "can_transfer_money": false,
      "can_deploy": false,
      "can_delete_external": false
    },
    "prompt_injection_surfaces": [
      "web",
      "documents"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 4,
      "A": 3,
      "C": 1
    },
    "flags": [
      "EXEC",
      "PRIVILEGED",
      "PERSISTENCE",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "CREDS_FILES",
      "CREDS_KEYCHAIN",
      "ACT_SEND_MESSAGE",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "PIPE_TO_SHELL",
        "name": "Pipe to Shell",
        "description": "Downloads and executes remote code (curl|bash pattern) in: scripts/install.sh"
      },
      {
        "code": "CRED_KEYCHAIN",
        "name": "Keychain Access",
        "description": "Accesses system keychain in: scripts/_checkpoint-full.sh"
      },
      {
        "code": "HIDDEN_INSTRUCTIONS",
        "name": "Hidden Instructions",
        "description": "Contains hidden instructions in comments/invisible chars in: SKILL.md"
      },
      {
        "code": "PERSISTENCE",
        "name": "Persistence Mechanism",
        "description": "Creates scheduled tasks or startup entries in: scripts/init-services.sh, scripts/install.sh, scripts/load-credentials.sh"
      },
      {
        "code": "PRIVILEGE_ESCALATION",
        "name": "Privilege Escalation",
        "description": "Uses elevated privileges (sudo/root) in: scripts/load-credentials.sh"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: scripts/_checkpoint-full.sh, scripts/checkpoint.sh, scripts/disk-cleanup.sh, scripts/restore-agent.sh, scripts/resurrect-from-solvr.sh"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_CRITICAL_ACCESS, MCP_SYS_PROCESS_MANIPULATION, INSTRUCTED_GIT_CLONE_AND_BUILD: Modifying system permissions or configuration"
      },
      {
        "code": "SOCIAL_ENGINEERING",
        "name": "Social Engineering Risk",
        "description": "SOCIAL_ENG_VAGUE_DESCRIPTION: Skill description is too vague or missing"
      },
      {
        "code": "COMMAND_INJECTION",
        "name": "Command Injection Risk",
        "description": "COMMAND_INJECTION_USER_INPUT, COMMAND_INJECTION_EVAL: User input used in command substitution - potential injection risk"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "DATA_EXFIL_SENSITIVE_FILES, DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS: Accessing sensitive system or credential files"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 10 security patterns (109 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "A": "A3: External actions (deploy/message/post)",
      "C": "C1: General content"
    }
  },
  "containment": {
    "level": "maximum",
    "required": [
      {
        "control": "APPROVE_SEND",
        "reason": "Can send messages"
      },
      {
        "control": "SANDBOX_CONTAINER",
        "reason": "Code execution capability"
      }
    ],
    "recommended": [
      {
        "control": "LOG_ACTIONS",
        "reason": "Audit trail for all actions"
      }
    ],
    "uncontained_risk": "Risk level depends on manual review of actual capabilities."
  },
  "risks": {
    "risks": [
      {
        "risk": "Pipe-to-shell pattern detected (curl|bash) in: scripts/install.sh",
        "severity": "critical",
        "mitigation": "Do not execute. Review source for malicious intent."
      },
      {
        "risk": "Keychain/credential store access in: scripts/_checkpoint-full.sh",
        "severity": "high",
        "mitigation": "Block keychain access or use isolated environment."
      },
      {
        "risk": "Unauthorized tool use: TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_CRITICAL_ACCESS, MCP_SYS_PROCESS_MANIPULATION, INSTRUCTED_GIT_CLONE_AND_BUILD",
        "severity": "critical",
        "mitigation": "Remove system modification commands"
      },
      {
        "risk": "Command injection risk: COMMAND_INJECTION_USER_INPUT, COMMAND_INJECTION_EVAL",
        "severity": "critical",
        "mitigation": "Validate and sanitize all user inputs before using in commands"
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Data exfiltration patterns: DATA_EXFIL_SENSITIVE_FILES, DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS",
        "severity": "high",
        "mitigation": "Do not access credential files or sensitive system files"
      }
    ],
    "limitations": [
      "Static analysis only - runtime behavior not verified"
    ]
  },
  "incident_response": {
    "kill_switch": [
      "Stop the agent process"
    ],
    "containment": [
      "Review logs for unexpected actions"
    ],
    "recovery": [
      "Depends on skill capabilities"
    ]
  },
  "evidence": [
    {
      "evidence_id": "EV:file-1",
      "type": "file_excerpt",
      "title": "scripts/_checkpoint-full.sh",
      "file_path": "scripts/_checkpoint-full.sh"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "scripts/_config-backup.sh",
      "file_path": "scripts/_config-backup.sh"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "scripts/_config-evaluators.sh",
      "file_path": "scripts/_config-evaluators.sh"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "scripts/_config-fix.sh",
      "file_path": "scripts/_config-fix.sh"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "scripts/_diagnose-claude.sh",
      "file_path": "scripts/_diagnose-claude.sh"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "scripts/_diagnose-condense.sh",
      "file_path": "scripts/_diagnose-condense.sh"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "scripts/audit-config.sh",
      "file_path": "scripts/audit-config.sh"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "scripts/checkpoint-decrypt.sh",
      "file_path": "scripts/checkpoint-decrypt.sh"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "scripts/checkpoint.sh",
      "file_path": "scripts/checkpoint.sh"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "scripts/compute-entity-similarity.py",
      "file_path": "scripts/compute-entity-similarity.py"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] scripts/_checkpoint-full.sh:389: chmod 600 \"$SECRETS_FILE\"",
      "file_path": "scripts/_checkpoint-full.sh"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] scripts/_checkpoint-full.sh:371: trap 'rm -rf \"$STAGING_DIR\"; rm -f \"$SECRETS_FILE\"' EXIT",
      "file_path": "scripts/_checkpoint-full.sh"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/_checkpoint-full.sh:1: #!/bin/bash",
      "file_path": "scripts/_checkpoint-full.sh"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] scripts/_config-backup.sh:21: SCRIPT_DIR=\"$(cd \"$(dirname \"$0\")\" && pwd)\"",
      "file_path": "scripts/_config-backup.sh"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] scripts/_config-backup.sh:131: chmod 600 \"$backup_file\"",
      "file_path": "scripts/_config-backup.sh"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/_config-backup.sh:1: #!/bin/bash",
      "file_path": "scripts/_config-backup.sh"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] scripts/_config-evaluators.sh:78: chmod 600 \"$CONFIG_FILE\"",
      "file_path": "scripts/_config-evaluators.sh"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/_config-evaluators.sh:1: #!/bin/bash",
      "file_path": "scripts/_config-evaluators.sh"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] scripts/_config-fix.sh:23: SCRIPT_DIR=\"$(cd \"$(dirname \"$0\")\" && pwd)\"",
      "file_path": "scripts/_config-fix.sh"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/_config-fix.sh:1: #!/bin/bash",
      "file_path": "scripts/_config-fix.sh"
    }
  ]
}