verify-workflow-review
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, potentially untrusted artifacts such as software code, documents, and articles. This creates a vulnerability surface where malicious instructions embedded within these artifacts could attempt to influence the agent's analysis or behavior during the review process.
- Ingestion points: External artifacts (code, documents, articles, deck, visual drafts) identified in the entry/exit and 'Step 3' sections.
- Boundary markers: Absent; the skill instructions do not specify the use of delimiters or 'ignore' directives to isolate external content from the agent's instructions.
- Capability inventory: The skill dispatches reviewer sub-agents and writes structured reports to
docs/features/<name>/04-review.md. - Sanitization: Absent; there is no evidence of content sanitization or validation before the artifacts are processed.
Audit Metadata