review-skill-format
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs read-only operations and basic text processing on local files within the expected directory structure. All shell commands used (test, wc, head, grep) are for validation purposes and do not execute content as code.- [SAFE]: No obfuscation, data exfiltration, or unauthorized network access patterns were identified. The skill's operations are confined to the local filesystem.- [SAFE]: The skill defines a clear ingestion point for untrusted data (external SKILL.md files), but its limited capabilities (pattern matching and line counting) do not present a viable attack surface for indirect prompt injection.
Audit Metadata