supply-chain-risk-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project files and dependency repositories which can serve as a vector for malicious instructions targeting the agent.
- Ingestion points: The skill reads local dependency manifest files (e.g., via
GrepandReadtools) and fetches metadata from external GitHub repositories using theghCLI tool, including README content and issue descriptions. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present when processing the external repository data.
- Capability inventory: The agent has access to
Bashfor command execution,Writefor file creation, andReadfor file inspection. - Sanitization: The instructions do not specify any sanitization, filtering, or validation for the content retrieved from external repositories before it is processed by the agent to generate the risk report.
Audit Metadata