skills/sharadchaturveda-coder/agency-agents-codex/agency-performance-benchmarker/Gen Agent Trust Hub
agency-performance-benchmarker
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow for ingesting and reporting on external performance metrics, which presents an indirect prompt injection surface.
- Ingestion points: Performance results and Real User Monitoring (RUM) data are processed into reports (SKILL.md).
- Boundary markers: The provided report templates in SKILL.md lack explicit delimiters or instructions to separate performance data from agent instructions.
- Capability inventory: The skill includes examples of generating JSON and HTML reports from test data (SKILL.md).
- Sanitization: The script examples do not demonstrate sanitization or validation of external content before it is interpolated into reporting templates.
Audit Metadata