global-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it ingests and evaluates untrusted data from survey drafts.
- Ingestion points: The skill reads
output/DRAFT.mdand auxiliary files in theoutline/directory (e.g.,outline.yml,taxonomy.yml) to perform its review. - Boundary markers: No explicit boundary markers or instructions to disregard embedded commands are utilized when processing the draft content within the LLM role prompt context.
- Capability inventory: The skill has the capability to write to
output/GLOBAL_REVIEW.mdand apply modifications tooutput/DRAFT.md. - Sanitization: There is no evidence of input sanitization or filtering applied to the draft content before it is processed by the AI or analyzed by the script logic.
Audit Metadata