Evolver 1.17.1

⬇ 213 downloads · ⭐ 2

High Risk

A self-evolution engine for AI agents. Features automated log analysis and protocol-constrained evolution with auditable assets.

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

⚠️ Hazard Flags

EXEC CODE_EXEC FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER FS_WRITE_SYSTEM FS_DELETE NET_EGRESS_ANY CREDS_ENV CREDS_FILES 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

Prompt injection patterns detected in: src/gep/selector.js high

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

Unauthorized tool use: MCP_SYS_FILE_DESTRUCTION, INSTRUCTED_BINARY_INSTALL critical

Mitigation: Remove destructive file operations.

Command injection risk: COMMAND_INJECTION_EVAL, MCP_CMD_DANGEROUS_SYSTEM critical

Mitigation: Avoid eval(), exec(), and compile(). Use safer alternatives like ast.literal_eval()

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION 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:evolver:1.18.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-16T15:14:23.890Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Evolver 1.17.1",
    "version": "1.18.0",
    "format": "agent_skill",
    "description": "A self-evolution engine for AI agents. Features automated log analysis and protocol-constrained evolution with auditable assets.",
    "publisher": "ClawHub",
    "source": {
      "channel": "clawhub",
      "slug": "evolver-1-17-1",
      "owner": "muguozi1",
      "downloads": 213,
      "stars": 2
    },
    "artifact": {
      "sha256": "7951adc3ef4d139ecacb276407f4efb4a3232117459fbb843f44170de647990f",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": true,
      "privilege_level": "user",
      "can_install_deps": false,
      "can_persist": false
    },
    "filesystem": {
      "reads_workspace": true,
      "reads_user_home": true,
      "reads_system": false,
      "writes_workspace": true,
      "writes_user_home": true,
      "writes_system": true,
      "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": [
      {
        "service": "code_hosting",
        "operations": [
          "read",
          "write"
        ]
      }
    ],
    "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": 4,
      "D": 3,
      "A": 3,
      "C": 1
    },
    "flags": [
      "EXEC",
      "CODE_EXEC",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_WRITE_SYSTEM",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "CREDS_FILES",
      "ACT_POST_PUBLIC",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: src/gep/selector.js"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: test/skillDistiller.test.js, src/ops/trigger.js, src/ops/skills_monitor.js, src/ops/self_repair.js, src/ops/lifecycle.js, src/ops/cleanup.js, src/gep/solidify.js, src/evolve.js, scripts/publish_public.js, scripts/build_public.js, index.js"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "MCP_SYS_FILE_DESTRUCTION, INSTRUCTED_BINARY_INSTALL: File destruction or wiping commands"
      },
      {
        "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_EVAL, MCP_CMD_DANGEROUS_SYSTEM: Dangerous code execution functions that can execute arbitrary code"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 5 security patterns (5 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D3: Credential access detected",
      "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": "Prompt injection patterns detected in: src/gep/selector.js",
        "severity": "high",
        "mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
      },
      {
        "risk": "Unauthorized tool use: MCP_SYS_FILE_DESTRUCTION, INSTRUCTED_BINARY_INSTALL",
        "severity": "critical",
        "mitigation": "Remove destructive file operations."
      },
      {
        "risk": "Command injection risk: COMMAND_INJECTION_EVAL, MCP_CMD_DANGEROUS_SYSTEM",
        "severity": "critical",
        "mitigation": "Avoid eval(), exec(), and compile(). Use safer alternatives like ast.literal_eval()"
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
        "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": "_meta.json",
      "file_path": "_meta.json"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "test/skillDistiller.test.js",
      "file_path": "test/skillDistiller.test.js"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "test/selector.test.js",
      "file_path": "test/selector.test.js"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "test/mutation.test.js",
      "file_path": "test/mutation.test.js"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "test/contentHash.test.js",
      "file_path": "test/contentHash.test.js"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "test/a2aProtocol.test.js",
      "file_path": "test/a2aProtocol.test.js"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "src/ops/trigger.js",
      "file_path": "src/ops/trigger.js"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "src/ops/skills_monitor.js",
      "file_path": "src/ops/skills_monitor.js"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "src/ops/self_repair.js",
      "file_path": "src/ops/self_repair.js"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "src/ops/lifecycle.js",
      "file_path": "src/ops/lifecycle.js"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] test/skillDistiller.test.js:207: validation: ['node test.js', 'rm -rf /', 'echo $(whoami)', 'npm test'],",
      "file_path": "test/skillDistiller.test.js"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_EVAL [CRITICAL] src/gep/analyzer.js:17: while ((match = failureRegex.exec(content)) !== null) {",
      "file_path": "src/gep/analyzer.js"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_CMD_DANGEROUS_SYSTEM [CRITICAL] src/evolve.js:274: const wmic = execSync('tasklist /FI \"IMAGENAME eq node.exe\" /NH', {",
      "file_path": "src/evolve.js"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] SKILL.md:104: npm install -g evolver@latest",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    }
  ]
}