HardStop

{
  "meta": {
    "document_id": "ssds:auto:hs:1.4.8",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T14:52:38.737Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "HardStop",
    "version": "1.4.8",
    "format": "agent_skill",
    "description": "\"ACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ. Check curl, wget, rm, sudo, apt, dpkg, chmod, dd, format, powershell, bash, sh. Check pipe patterns like | sh or | bash. Check shell wrappers like bash -c, xargs, find -exec. Check cloud CLI (aws, gcloud, kubectl, terraform). Check when user says sysadmin told me, Stack Overflow says, is this safe, can I run. Block reading of .env, .ssh, .aws, and credential files. This skill blocks dangerous commands and warns on risky ones. ALWAYS apply the safety protocol from this document before responding about any command.\"",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "d29b3bed24677c1b97ca2f5d6decc0eba367975d220fe622323bcb2f2c5743ed",
      "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": false,
      "reads_user_home": true,
      "reads_system": false,
      "writes_workspace": false,
      "writes_user_home": false,
      "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": false
    },
    "services": [],
    "actions": {
      "can_send_messages": false,
      "can_post_public": true,
      "can_purchase": false,
      "can_transfer_money": false,
      "can_deploy": false,
      "can_delete_external": true
    },
    "prompt_injection_surfaces": [
      "web",
      "documents"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 4,
      "A": 3,
      "C": 1
    },
    "flags": [
      "EXEC",
      "PRIVILEGED",
      "PERSISTENCE",
      "FS_READ_USER",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "CREDS_FILES",
      "ACT_POST_PUBLIC",
      "ACT_DELETE_EXTERNAL",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "PIPE_TO_SHELL",
        "name": "Pipe to Shell",
        "description": "Downloads and executes remote code (curl|bash pattern) in: SKILL.md"
      },
      {
        "code": "SECURITY_BYPASS",
        "name": "Security Bypass",
        "description": "Attempts to disable security features in: SKILL.md"
      },
      {
        "code": "CRED_SSH",
        "name": "SSH Key Access",
        "description": "Accesses SSH keys in: SKILL.md"
      },
      {
        "code": "CRED_CLOUD",
        "name": "Cloud Credential Access",
        "description": "Accesses cloud credentials (AWS/GCP/Azure) in: SKILL.md"
      },
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: SKILL.md"
      },
      {
        "code": "PERSISTENCE",
        "name": "Persistence Mechanism",
        "description": "Creates scheduled tasks or startup entries in: SKILL.md"
      },
      {
        "code": "PRIVILEGE_ESCALATION",
        "name": "Privilege Escalation",
        "description": "Uses elevated privileges (sudo/root) in: SKILL.md"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: SKILL.md"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "INSTRUCTED_BINARY_INSTALL, MCP_SYS_FILE_DESTRUCTION: Instructs agent to install external binary or package"
      },
      {
        "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": "MCP_CMD_REVERSE_SHELL, MCP_CMD_DANGEROUS_SYSTEM, MCP_CMD_NETWORK_TOOLS: Reverse shell pattern detected"
      },
      {
        "code": "TOOL_POISONING",
        "name": "Tool Poisoning",
        "description": "Hidden secondary behavior detected: MCP_TOOL_POISONING_DECEPTION, MCP_TOOL_POISONING_REMOTE_STORAGE"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 12 security patterns (8 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_POST",
        "reason": "Can post publicly"
      },
      {
        "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: SKILL.md",
        "severity": "critical",
        "mitigation": "Do not execute. Review source for malicious intent."
      },
      {
        "risk": "Security bypass pattern detected in: SKILL.md",
        "severity": "critical",
        "mitigation": "This skill attempts to disable security features. Do not use."
      },
      {
        "risk": "SSH key access patterns in: SKILL.md",
        "severity": "high",
        "mitigation": "Verify legitimate need for SSH access. Consider sandboxing."
      },
      {
        "risk": "Cloud credential access patterns in: SKILL.md",
        "severity": "high",
        "mitigation": "Verify legitimate need for cloud credential access."
      },
      {
        "risk": "Prompt injection patterns detected in: SKILL.md",
        "severity": "high",
        "mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
      },
      {
        "risk": "Unauthorized tool use: INSTRUCTED_BINARY_INSTALL, MCP_SYS_FILE_DESTRUCTION",
        "severity": "critical",
        "mitigation": "Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments"
      },
      {
        "risk": "Command injection risk: MCP_CMD_REVERSE_SHELL, MCP_CMD_DANGEROUS_SYSTEM, MCP_CMD_NETWORK_TOOLS",
        "severity": "critical",
        "mitigation": "Remove reverse shell commands."
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Tool poisoning: hidden behaviors detected (MCP_TOOL_POISONING_DECEPTION, MCP_TOOL_POISONING_REMOTE_STORAGE)",
        "severity": "critical",
        "mitigation": "Remove deceptive language. Tools must be transparent about their behavior."
      }
    ],
    "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": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "_meta.json",
      "file_path": "_meta.json"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] SKILL.md:102: | `curl/wget ... \\| bash` | Executes untrusted remote code |",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_TOOL_POISONING_DECEPTION [CRITICAL] SKILL.md:379: This command would: [what it actually does]",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_TOOL_POISONING_REMOTE_STORAGE [MEDIUM] SKILL.md:467: This file may contain sensitive credentials.",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "MCP_CMD_REVERSE_SHELL [CRITICAL] SKILL.md:100: | `bash -i >& /dev/tcp/` | Reverse shell, attacker access |",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "MCP_CMD_DANGEROUS_SYSTEM [CRITICAL] SKILL.md:4: description: \"ACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ. Check curl",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "MCP_CMD_NETWORK_TOOLS [HIGH] SKILL.md:101: | `nc -e /bin/sh` | Reverse shell variant |",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] SKILL.md:97: | `rm -rf ~/` or `rm -rf ~/*` | Deletes entire home directory |",
      "file_path": "SKILL.md"
    }
  ]
}