critique
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill acts as a report-only orchestrator for specialized analysis agents.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes external files and conversation context.
- Ingestion points: Files and conversation history identified in the scope gathering phase (SKILL.md).
- Boundary markers: Uses
[CONTEXT]tags to delimit external data from instructions. - Capability inventory: Limited to analysis tasks via general-purpose subagents using the
Tasktool; no file writes or network exfiltration detected. - Sanitization: No explicit sanitization is performed on ingested code snippets.
Audit Metadata