ClawHub
Back to skill

Security audit

agent-bom ingest

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local inventory validation and vulnerability-reporting workflow with optional, purpose-aligned external lookups and operator-controlled push behavior.

Before installing, confirm you trust the agent-bom tool itself and understand that optional enrichment may send package or advisory lookup data to OSV or GitHub, and optional control-plane push should only be enabled with a destination URL and token you control.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
- agent-bom
      env: []
      credentials: none
    credential_policy: "No cloud credentials are required. Optional control-plane push uses an operator-provided agent-bom API token; never ask users to paste that token into chat and never print it."
    optional_env:
      - AGENT_BOM_API_KEY
      - AGENT_BOM_PUSH_URL

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
purpose: "Optional push into the operator-owned agent-bom control plane"
        auth: true
        optional: true
      - url: "https://api.osv.dev/v1"
        purpose: "Optional package vulnerability lookup during local scan"
        auth: false
        optional: true

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
purpose: "Optional package vulnerability lookup during local scan"
        auth: false
        optional: true
      - url: "https://api.github.com/advisories"
        purpose: "Optional GitHub Advisory enrichment during local scan"
        auth: false
        optional: true

Static analysis

No suspicious patterns detected.