superpowers-review
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a checklist and severity levels for manual or AI-assisted code review. It does not include any commands, scripts, or external references that could be used for malicious purposes.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze external code changes, which serves as an ingestion point for untrusted data. However, the skill lacks any tools or capabilities that could be exploited through this surface. Evidence Chain: 1. Ingestion points: Code changes provided to the agent for review (SKILL.md instructions); 2. Boundary markers: Absent; 3. Capability inventory: None (no subprocess calls, network ops, or file writes); 4. Sanitization: Absent.
Audit Metadata