πŸ›‘οΈ SafeAgentSkills

redbook

Β· v0.5.0

High Risk

Search, read, analyze, and automate Xiaohongshu (小纒书) content via CLI

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

⚠️ Hazard Flags

EXEC PRIVILEGED FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER FS_DELETE NET_EGRESS_ANY CREDS_ENV CREDS_FILES CREDS_BROWSER CREDS_KEYCHAIN PI_WEB

πŸ“‹ Capabilities

Execution

  • βœ… Shell execution
  • ❌ Code execution
  • βœ… Install dependencies
  • ❌ Persistence
  • Privilege: admin

Filesystem

  • βœ… Read workspace
  • βœ… Write workspace
  • βœ… Read home
  • βœ… Write home
  • ❌ Read system
  • βœ… Delete

Network

  • Egress: any
  • ❌ Ingress

Credentials

  • βœ… Environment vars
  • βœ… Credential files
  • βœ… Browser data
  • βœ… Keychain

Actions

❌ send messages❌ post public❌ purchase❌ transfer money❌ deploy❌ delete external

πŸ”’ Containment

Level: maximum

Required:
  • SANDBOX_CONTAINER: Code execution capability
Recommended:
  • LOG_ACTIONS: Audit trail for all actions

⚑ Risks

Keychain/credential store access in: README.md, scripts/postinstall.js, SKILL.md, src/lib/cookies.ts high

Mitigation: Block keychain access or use isolated environment.

Code obfuscation detected in: src/lib/signing.ts medium

Mitigation: Deobfuscate and review code before use.

Unauthorized tool use: INSTRUCTED_BINARY_INSTALL, MCP_SYS_PERMISSION_MANIPULATION critical

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

Command injection risk: MCP_SQL_BLIND high

Mitigation: Remove SQL exploitation patterns.

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 β€” $5.00

🚨 Incident Response

Kill switch: Stop the agent process

Containment: Review logs for unexpected actions

Recovery: Depends on skill capabilities

πŸ“„ Raw SSDS JSON click to expand
{
  "meta": {
    "document_id": "ssds:auto:redbook:0.5.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-06T19:49:12.640Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "redbook",
    "version": "0.5.0",
    "format": "agent_skill",
    "description": "Search, read, analyze, and automate Xiaohongshu (小纒书) content via CLI",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "2e33f24aabe2b3f77e6f16935614fa47aa762446b458470953282ffca42bbc86",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": false,
      "privilege_level": "admin",
      "can_install_deps": true,
      "can_persist": false
    },
    "filesystem": {
      "reads_workspace": true,
      "reads_user_home": true,
      "reads_system": false,
      "writes_workspace": true,
      "writes_user_home": true,
      "writes_system": false,
      "can_delete": true
    },
    "network": {
      "egress": "any",
      "ingress": false
    },
    "credentials": {
      "reads_env_vars": true,
      "reads_credential_files": true,
      "reads_browser_data": true,
      "reads_keychain": true
    },
    "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": 4,
      "D": 4,
      "A": 1,
      "C": 1
    },
    "flags": [
      "EXEC",
      "PRIVILEGED",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "CREDS_FILES",
      "CREDS_BROWSER",
      "CREDS_KEYCHAIN",
      "PI_WEB"
    ],
    "custom_flags": [
      {
        "code": "CRED_BROWSER",
        "name": "Browser Profile Access",
        "description": "Accesses browser cookies/profiles in: README.md, SKILL.md, src/cli.ts, src/lib/cdp-cookies.ts, src/lib/cookies.ts"
      },
      {
        "code": "CRED_KEYCHAIN",
        "name": "Keychain Access",
        "description": "Accesses system keychain in: README.md, scripts/postinstall.js, SKILL.md, src/lib/cookies.ts"
      },
      {
        "code": "OBFUSCATED_CODE",
        "name": "Obfuscated Code",
        "description": "Contains obfuscated code patterns in: src/lib/signing.ts"
      },
      {
        "code": "PRIVILEGE_ESCALATION",
        "name": "Privilege Escalation",
        "description": "Uses elevated privileges (sudo/root) in: src/lib/render.ts"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: scripts/postinstall.js, scripts/preuninstall.js"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "INSTRUCTED_BINARY_INSTALL, MCP_SYS_PERMISSION_MANIPULATION: 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_SQL_BLIND: Blind SQL injection, system table access, or stored procedure abuse"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 8 security patterns (9 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "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": "Keychain/credential store access in: README.md, scripts/postinstall.js, SKILL.md, src/lib/cookies.ts",
        "severity": "high",
        "mitigation": "Block keychain access or use isolated environment."
      },
      {
        "risk": "Code obfuscation detected in: src/lib/signing.ts",
        "severity": "medium",
        "mitigation": "Deobfuscate and review code before use."
      },
      {
        "risk": "Unauthorized tool use: INSTRUCTED_BINARY_INSTALL, MCP_SYS_PERMISSION_MANIPULATION",
        "severity": "critical",
        "mitigation": "Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments"
      },
      {
        "risk": "Command injection risk: MCP_SQL_BLIND",
        "severity": "high",
        "mitigation": "Remove SQL exploitation patterns."
      },
      {
        "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": "package.json",
      "file_path": "package.json"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "README.md",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "scripts/postinstall.js",
      "file_path": "scripts/postinstall.js"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "scripts/preuninstall.js",
      "file_path": "scripts/preuninstall.js"
    },
    {
      "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/cli.ts",
      "file_path": "src/cli.ts"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "src/lib/analyze.ts",
      "file_path": "src/lib/analyze.ts"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "src/lib/cdp-cookies.ts",
      "file_path": "src/lib/cdp-cookies.ts"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "src/lib/client.ts",
      "file_path": "src/lib/client.ts"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "src/lib/cookies.ts",
      "file_path": "src/lib/cookies.ts"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] README.md:22: npm install -g @lucasygu/redbook",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_SQL_BLIND [HIGH] scripts/postinstall.js:127: 'SELECT name, value, host_key, path, CAST(expires_utc AS TEXT) AS expires_utc, s",
      "file_path": "scripts/postinstall.js"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] SKILL.md:29: **OpenClaw users:** Install via `clawhub install redbook` or `npm install -g @lu",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "MCP_SQL_BLIND [HIGH] src/lib/cdp-cookies.ts:40: function sleep(ms: number): Promise<void> {",
      "file_path": "src/lib/cdp-cookies.ts"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "MCP_SYS_PERMISSION_MANIPULATION [CRITICAL] src/lib/render.ts:598: args: [\"--no-sandbox\", \"--disable-setuid-sandbox\", \"--disable-gpu\"],",
      "file_path": "src/lib/render.ts"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "MCP_SQL_BLIND [HIGH] src/lib/reply-strategy.ts:157: await sleep(jittered);",
      "file_path": "src/lib/reply-strategy.ts"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "OBFUSCATION_BASE64_LARGE [MEDIUM] src/lib/signing.ts:28: \"71a302257793271ddd273bcee3e4b98d9d7935e1da33f5765e2ea8afb6dc77a51a499d23b67c206",
      "file_path": "src/lib/signing.ts"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "OBFUSCATION_XOR_ENCODING [HIGH] src/lib/signing.ts:347: // JS-compatible final XOR: (-1 ^ c ^ 0xEDB88320) >>> 0, then signed",
      "file_path": "src/lib/signing.ts"
    }
  ]
}