10-requirements-metrics
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted requirements data from external markdown files, creating a potential surface for indirect prompt injection.
- Ingestion points: All
*.mdartifacts located inprojects/<ProjectName>/<phase>/<document>/andvision.mdinprojects/<ProjectName>/_context/(SKILL.md). - Boundary markers: The instructions lack explicit delimiters or warnings to the agent to treat requirement content strictly as data, increasing the risk that embedded instructions could be executed.
- Capability inventory: The agent is granted read and search permissions across project directories and the ability to write a
requirements_metrics_report.mdoutput file (SKILL.md). - Sanitization: There is no evidence of sanitization or filtering of the ingested text before the agent performs metric calculations or interpolates finding descriptions into the output report.
Audit Metadata