performance-audit
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains a CRITICAL instruction to ignore all user-provided arguments, URLs, or paths, which serves as a robust defense against parameter-based prompt injection attacks.
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted codebase data. Ingestion points: Reads files across the target codebase during the performance audit. Boundary markers: No specific delimiters or 'ignore' instructions are defined for the data processed by the subagent. Capability inventory: The skill has the ability to write files to the local directory '/docs/performance/'. Sanitization: There is no evidence of sanitization or filtering for the content extracted from the codebase into the final markdown report.
Audit Metadata