Counterclaw Core

· v1.1.1

Medium Risk

Defensive interceptor for prompt injection and basic PII masking.

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

⚠️ Hazard Flags

EXEC PERSISTENCE FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER NET_EGRESS_ANY CREDS_ENV CREDS_FILES CREDS_KEYCHAIN ACT_POST_PUBLIC PI_WEB PI_DOCUMENTS

📋 Capabilities

Execution

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

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_POST: Can post publicly
SANDBOX_CONTAINER: Code execution capability

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Keychain/credential store access in: README.md high

Mitigation: Block keychain access or use isolated environment.

Prompt injection patterns detected in: email_protector.py, README.md, SKILL.md, src/counterclaw/scanner.py, tests/test_email_protection.py, tests/test_scanner.py high

Mitigation: Review SKILL.md for hidden instructions. Do not use with untrusted input.

Unauthorized tool use: INSTRUCTED_BINARY_INSTALL, MCP_SYS_CRITICAL_ACCESS high

Mitigation: Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low

Mitigation: Provide clear, detailed description of skill functionality

Data exfiltration patterns: INSTRUCTED_SENSITIVE_SERVICE_ACCESS high

Mitigation: Clearly document which sensitive services are accessed and why; use minimal required permissions

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:counterclaw:1.1.1",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T13:06:48.787Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Counterclaw Core",
    "version": "1.1.1",
    "format": "agent_skill",
    "description": "Defensive interceptor for prompt injection and basic PII masking.",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "17ae9de57419950fa9a703d805bca0584919c72e0a324644c9b08c08d791cf04",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": false,
      "privilege_level": "user",
      "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": false
    },
    "network": {
      "egress": "any",
      "ingress": false
    },
    "credentials": {
      "reads_env_vars": true,
      "reads_credential_files": true,
      "reads_browser_data": false,
      "reads_keychain": true
    },
    "services": [],
    "actions": {
      "can_send_messages": false,
      "can_post_public": true,
      "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": 3,
      "D": 4,
      "A": 3,
      "C": 1
    },
    "flags": [
      "EXEC",
      "PERSISTENCE",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "CREDS_FILES",
      "CREDS_KEYCHAIN",
      "ACT_POST_PUBLIC",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "CRED_KEYCHAIN",
        "name": "Keychain Access",
        "description": "Accesses system keychain in: README.md"
      },
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: email_protector.py, README.md, SKILL.md, src/counterclaw/scanner.py, tests/test_email_protection.py, tests/test_scanner.py"
      },
      {
        "code": "PERSISTENCE",
        "name": "Persistence Mechanism",
        "description": "Creates scheduled tasks or startup entries in: README.md"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "INSTRUCTED_BINARY_INSTALL, MCP_SYS_CRITICAL_ACCESS: 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": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "INSTRUCTED_SENSITIVE_SERVICE_ACCESS: Instructs agent to access sensitive services (email, calendar, contacts, drive)"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 6 security patterns (8 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H3: Shell/code execution or persistence 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": "Keychain/credential store access in: README.md",
        "severity": "high",
        "mitigation": "Block keychain access or use isolated environment."
      },
      {
        "risk": "Prompt injection patterns detected in: email_protector.py, README.md, SKILL.md, src/counterclaw/scanner.py, tests/test_email_protection.py, tests/test_scanner.py",
        "severity": "high",
        "mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
      },
      {
        "risk": "Unauthorized tool use: INSTRUCTED_BINARY_INSTALL, MCP_SYS_CRITICAL_ACCESS",
        "severity": "high",
        "mitigation": "Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments"
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Data exfiltration patterns: INSTRUCTED_SENSITIVE_SERVICE_ACCESS",
        "severity": "high",
        "mitigation": "Clearly document which sensitive services are accessed and why; use minimal required permissions"
      }
    ],
    "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": "email_protector.py",
      "file_path": "email_protector.py"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "pyproject.toml",
      "file_path": "pyproject.toml"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "README.md",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "send_protected_email.sh",
      "file_path": "send_protected_email.sh"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "src/counterclaw_cli/__init__.py",
      "file_path": "src/counterclaw_cli/__init__.py"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "src/counterclaw/__init__.py",
      "file_path": "src/counterclaw/__init__.py"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "src/counterclaw/middleware.py",
      "file_path": "src/counterclaw/middleware.py"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "src/counterclaw/scanner.py",
      "file_path": "src/counterclaw/scanner.py"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "tests/test_email_protection.py",
      "file_path": "tests/test_email_protection.py"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "PROMPT_INJECTION_IGNORE_INSTRUCTIONS [HIGH] README.md:38: - \"Ignore previous instructions\"",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "PROMPT_INJECTION_BYPASS_POLICY [HIGH] README.md:11: Your AI agent is vulnerable. Attackers use prompt injections to make your agent ",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] README.md:58: pip install counterclaw-core",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] send_protected_email.sh:1: #!/bin/bash",
      "file_path": "send_protected_email.sh"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "PROMPT_INJECTION_IGNORE_INSTRUCTIONS [HIGH] SKILL.md:50: result = interceptor.check_input(\"{{EXAMPLE: ignore previous instructions}}\")",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] SKILL.md:5: install: \"pip install .\"",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "INSTRUCTED_SENSITIVE_SERVICE_ACCESS [HIGH] SKILL.md:33: 2. **Email Integration (network):** `send_protected_email.sh` — requires gog CLI",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    }
  ]
}