node-supply-chain
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's audit script analyzes untrusted repository data, which could contain hidden instructions intended to influence the agent's behavior.
- Ingestion points: The file
scripts/audit_supply_chain.pyreads and processes content frompackage.json,.npmrc,.yarnrc.yml,.pnpm-workspace.yaml, and GitHub workflow files (.github/workflows/*.yml). - Boundary markers: The script ingests raw text from these files to perform regex-based analysis without employing specific boundary markers to isolate data from the agent's instruction context.
- Capability inventory: The skill possesses capabilities for reading local filesystem content and recommending configuration changes; combined with the ingestion of external data, this creates a standard indirect injection surface.
- Sanitization: While the script uses specific regex patterns to detect security violations, it does not sanitize or escape the processed text before it is returned to the agent's reasoning context.
Audit Metadata