Trail Of Bits Security
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data (source code provided by users for review). This creates an attack surface where instructions embedded in the code (such as malicious comments) could attempt to influence the agent's behavior.
- Ingestion points: Source code provided by users during the code review process.
- Boundary markers: Absent. The instructions do not provide specific delimiters or warnings to treat the code strictly as data.
- Capability inventory: The skill body contains no scripts or subprocess calls; however, the agent's response is the primary output.
- Sanitization: Absent. The skill does not define methods to sanitize or escape potentially malicious instructions within the analyzed code.
Audit Metadata