synthesize-review-findings
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and processes external data provided as 'reviewer verdicts', which creates a surface for indirect prompt injection.
- Ingestion points: The skill processes external findings and verdicts as described in SKILL.md.
- Boundary markers: The instructions lack explicit requirements for using delimiters or warnings to ignore instructions embedded within the source findings.
- Capability inventory: The skill has no identified dangerous capabilities; it lacks network access, file writing permissions, and command execution tools.
- Sanitization: There are no instructions for sanitizing or escaping the content of the source findings before synthesis.
Audit Metadata