review-skill
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core function is to ingest and process untrusted data from other skills.
- Ingestion points: Reads
SKILL.md, scripts, and other files from paths provided by the user or found in~/.claude/skills/(SKILL.md, Step 1 & 2). - Boundary markers: None specified. The instructions do not include delimiters or warnings to ignore instructions found within the files being reviewed.
- Capability inventory: File system read access to user-defined paths and skill directories; implied file-write capability when offering to "apply suggested fixes automatically" (SKILL.md, Step 5).
- Sanitization: No sanitization or validation of the content of the reviewed files is mentioned.
- Risk: If a malicious skill being reviewed contains prompt injection (e.g., instructions to delete files instead of reviewing them), the agent might follow those instructions while performing the audit.
Audit Metadata