review
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted code and git diffs, which creates a surface for indirect prompt injection if malicious instructions are embedded in the analyzed code. 1. Ingestion points: SKILL.md (Procedure steps 1 and 3 via git and Read tools). 2. Boundary markers: Absent. 3. Capability inventory: The agent has access to Bash, Write, Read, Glob, and Grep tools (SKILL.md frontmatter). 4. Sanitization: Absent.
- [COMMAND_EXECUTION]: The preamble section executes local shell commands for environment discovery and sources an initialization script.
- [DATA_EXFILTRATION]: The skill reads the full content of source files and git diffs to perform its analysis, which is required for its intended purpose but involves accessing project data.
Audit Metadata