perf-investigation-logger
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill captures verbatim user quotes which creates a potential surface for indirect prompt injection if the logs are later processed by an AI agent. This is a low-risk concern consistent with the skill's primary logging purpose.
- Ingestion points: User-provided verbatim quotes are captured and logged (SKILL.md).
- Boundary markers: Quotes are wrapped in double-quote delimiters in the specified output format.
- Capability inventory: The skill appends data to local files in the
{state-dir}/perf/investigations/directory. - Sanitization: No explicit sanitization or escaping of user input is performed before logging.
Audit Metadata