quality-status-digest
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from external sources and incorporate it into generated reports, creating a surface for potential injection.\n
- Ingestion points: Untrusted data is read from sources such as
trackers/board-export-*.csv,ci/runs-*.csv,quarantine.json, anddefects/production-defects.csv.\n - Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' instructions when processing the content of bug reports or log notes.\n
- Capability inventory: The skill has read access to the local metrics files and write access to report directories including
quality-digest/,docs/, andportfolio/.\n - Sanitization: There is no explicit instruction to sanitize, validate, or escape the content of external data fields before they are interpolated into the Markdown report outputs.
Audit Metadata