full-repo-review
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script at
~/.claude/scripts/score-component.pyto perform deterministic health checks on repository components. This dependency is expected to exist within the environment's configuration. - [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by ingesting and analyzing arbitrary source code from the repository.
- Ingestion points: Phase 1 discovery commands identifying Python scripts, hooks, skills, and agents across the codebase.
- Boundary markers: Absent; the instructions do not implement specific delimiters or 'ignore' instructions for the ingested code content.
- Capability inventory: The skill utilizes
Bash,Read,Write,Glob, andGreptools to facilitate the discovery and reporting process. - Sanitization: Absent; the ingested content is analyzed as-is without validation or filtering.
Audit Metadata