Repo PR Triage

· v1.0.0

High Risk

Triage GitHub PRs and issues using vision-based scoring. Use when a user wants to prioritize, score, review, de-duplicate, or batch-process open pull requests or issues against their project's mission and values. Supports onboarding (interview repo owner to build vision doc), scanning (score PRs with rubric), and reporting (generate actionable markdown reports). Works with any GitHub repo via gh CLI.

H:4 D:2 A:1 C:1

⚠️ Hazard Flags

EXEC FS_READ_WORKSPACE FS_WRITE_WORKSPACE FS_WRITE_SYSTEM FS_DELETE NET_EGRESS_ANY 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:

SANDBOX_CONTAINER: Code execution capability

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Prompt injection patterns detected in: scripts/test_scan.py high

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

Unauthorized tool use: MCP_SYS_FILE_DESTRUCTION critical

Mitigation: Remove destructive file operations.

Command injection risk: MCP_SQL_BLIND high

Mitigation: Remove SQL exploitation patterns.

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION low

Mitigation: Provide clear, detailed description of skill functionality

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:pr-triage:1.0.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T14:10:24.615Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Repo PR Triage",
    "version": "1.0.0",
    "format": "agent_skill",
    "description": "Triage GitHub PRs and issues using vision-based scoring. Use when a user wants to prioritize, score, review, de-duplicate, or batch-process open pull requests or issues against their project's mission and values. Supports onboarding (interview repo owner to build vision doc), scanning (score PRs with rubric), and reporting (generate actionable markdown reports). Works with any GitHub repo via gh CLI.",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "8488460f6f8fac1fda513d04276fadf842048a4a38527515dff7db279575eb8a",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": false,
      "privilege_level": "user",
      "can_install_deps": false,
      "can_persist": false
    },
    "filesystem": {
      "reads_workspace": true,
      "reads_user_home": false,
      "reads_system": false,
      "writes_workspace": true,
      "writes_user_home": false,
      "writes_system": true,
      "can_delete": true
    },
    "network": {
      "egress": "any",
      "ingress": false
    },
    "credentials": {
      "reads_env_vars": false,
      "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",
      "documents"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 2,
      "A": 1,
      "C": 1
    },
    "flags": [
      "EXEC",
      "FS_READ_WORKSPACE",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_SYSTEM",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: scripts/test_scan.py"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: scripts/test_onboard.py, scripts/test_report.py, scripts/test_scan.py"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "MCP_SYS_FILE_DESTRUCTION: File destruction or wiping commands"
      },
      {
        "code": "SOCIAL_ENGINEERING",
        "name": "Social Engineering Risk",
        "description": "SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION: Skill description is too vague or missing"
      },
      {
        "code": "COMMAND_INJECTION",
        "name": "Command Injection Risk",
        "description": "MCP_SQL_BLIND: Blind SQL injection, system table access, or stored procedure abuse"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 5 security patterns (6 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D2: Network + file access",
      "A": "A1: Local side effects only",
      "C": "C1: General content"
    }
  },
  "containment": {
    "level": "maximum",
    "required": [
      {
        "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": "Prompt injection patterns detected in: scripts/test_scan.py",
        "severity": "high",
        "mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
      },
      {
        "risk": "Unauthorized tool use: MCP_SYS_FILE_DESTRUCTION",
        "severity": "critical",
        "mitigation": "Remove destructive file operations."
      },
      {
        "risk": "Command injection risk: MCP_SQL_BLIND",
        "severity": "high",
        "mitigation": "Remove SQL exploitation patterns."
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      }
    ],
    "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/onboard.py",
      "file_path": "scripts/onboard.py"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "scripts/report.py",
      "file_path": "scripts/report.py"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "scripts/scan.py",
      "file_path": "scripts/scan.py"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "scripts/test_onboard.py",
      "file_path": "scripts/test_onboard.py"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "scripts/test_report.py",
      "file_path": "scripts/test_report.py"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "scripts/test_scan.py",
      "file_path": "scripts/test_scan.py"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "_meta.json",
      "file_path": "_meta.json"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "MCP_SQL_BLIND [HIGH] scripts/scan.py:41: time.sleep(wait)",
      "file_path": "scripts/scan.py"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] scripts/test_onboard.py:112: ctx = {\"metadata\": {\"name\": \"$(rm -rf /)\", \"description\": \"\", \"stargazerCount\": ",
      "file_path": "scripts/test_onboard.py"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] scripts/test_report.py:86: pr = _make_scored_pr(title=\"$(rm -rf /)\")",
      "file_path": "scripts/test_report.py"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] scripts/test_scan.py:34: result = scan.parse_repo(\"https://github.com/owner/repo; rm -rf /\")",
      "file_path": "scripts/test_scan.py"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_ANTHROPIC_IMPERSONATION [MEDIUM] SKILL.md:104: model: anthropic/claude-sonnet-4-20250514",
      "file_path": "SKILL.md"
    }
  ]
}