Meerkat Governance

· v1.0.4

Medium Risk

AI governance API with two endpoints. Shield scans untrusted content for prompt injection and threats. Verify checks AI output for hallucinations, numerical errors, and manipulation against source data. Returns structured results with trust scores and remediation guidance. Full audit trail.

H:3 D:4 A:0 C:1

⚠️ Hazard Flags

NET_EGRESS_ANY CREDS_ENV PI_WEB

📋 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

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low

Mitigation: Provide clear, detailed description of skill functionality

Tool poisoning: hidden behaviors detected (MCP_TOOL_POISONING_DECEPTION) critical

Mitigation: Remove deceptive language. Tools must be transparent about their behavior.

Data exfiltration patterns: MCP_EXFIL_EXTERNAL_UPLOAD high

Mitigation: Document all external data transfers. Remove suspicious upload references.

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:meerkat-governance:1.0.4",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T14:31:05.433Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Meerkat Governance",
    "version": "1.0.4",
    "format": "agent_skill",
    "description": "AI governance API with two endpoints. Shield scans untrusted content for prompt injection and threats. Verify checks AI output for hallucinations, numerical errors, and manipulation against source data. Returns structured results with trust scores and remediation guidance. Full audit trail.",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "ba2564064eb4cf5651ddb3cbb2d8abcd56200fb1c2bb0bad8ee8ecc3a6b5081d",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": false,
      "can_exec_code": false,
      "privilege_level": "user",
      "can_install_deps": false,
      "can_persist": false
    },
    "filesystem": {
      "reads_workspace": false,
      "reads_user_home": false,
      "reads_system": false,
      "writes_workspace": false,
      "writes_user_home": false,
      "writes_system": false,
      "can_delete": false
    },
    "network": {
      "egress": "any",
      "ingress": false
    },
    "credentials": {
      "reads_env_vars": true,
      "reads_credential_files": false,
      "reads_browser_data": false,
      "reads_keychain": false
    },
    "services": [],
    "actions": {
      "can_send_messages": false,
      "can_post_public": false,
      "can_purchase": false,
      "can_transfer_money": false,
      "can_deploy": false,
      "can_delete_external": false
    },
    "prompt_injection_surfaces": [
      "web"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 3,
      "D": 4,
      "A": 0,
      "C": 1
    },
    "flags": [
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "PI_WEB"
    ],
    "custom_flags": [
      {
        "code": "SOCIAL_ENGINEERING",
        "name": "Social Engineering Risk",
        "description": "SOCIAL_ENG_VAGUE_DESCRIPTION: Skill description is too vague or missing"
      },
      {
        "code": "TOOL_POISONING",
        "name": "Tool Poisoning",
        "description": "Hidden secondary behavior detected: MCP_TOOL_POISONING_DECEPTION"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "MCP_EXFIL_EXTERNAL_UPLOAD: Description mentions uploading data to external servers"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 3 security patterns (3 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H3: Shell/code execution or persistence detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "A": "A0: No side effects detected",
      "C": "C1: General content"
    }
  },
  "containment": {
    "level": "maximum",
    "required": [],
    "recommended": [
      {
        "control": "LOG_ACTIONS",
        "reason": "Audit trail for all actions"
      }
    ],
    "uncontained_risk": "Risk level depends on manual review of actual capabilities."
  },
  "risks": {
    "risks": [
      {
        "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)",
        "severity": "critical",
        "mitigation": "Remove deceptive language. Tools must be transparent about their behavior."
      },
      {
        "risk": "Data exfiltration patterns: MCP_EXFIL_EXTERNAL_UPLOAD",
        "severity": "high",
        "mitigation": "Document all external data transfers. Remove suspicious upload references."
      }
    ],
    "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": "_meta.json",
      "file_path": "_meta.json"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_TOOL_POISONING_DECEPTION [CRITICAL] SKILL.md:22: Meerkat processes content in memory and discards it after the response. Only tru",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_EXFIL_EXTERNAL_UPLOAD [HIGH] SKILL.md:31: curl -s -X POST https://api.meerkatplatform.com/v1/shield \\",
      "file_path": "SKILL.md"
    }
  ]
}