wheel-reinvention-audit
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of code diffs, implementation plans, and project manifests (e.g., package.json, requirements.txt) to perform its audit.
- Ingestion points: Reads project manifests, lockfiles, configuration files, and code diffs as specified in the 'Procedure' section of SKILL.md.
- Boundary markers: None explicitly defined in the prompt instructions to isolate external content from instructions.
- Capability inventory: The skill performs analysis and reporting; it does not contain instructions for file-writing, network operations, or subprocess execution.
- Sanitization: The instructions do not specify sanitization or escaping mechanisms for the code being reviewed.
- Risk: While the skill processes untrusted code that could contain adversarial prompts, the impact is limited to the agent providing a biased or incorrect audit report, as the skill lacks dangerous capabilities to execute.
Audit Metadata