review-context-hub
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses bash commands like find, git, and the GitHub CLI (gh) to audit repository state and metadata.
- [PROMPT_INJECTION]: Vulnerable to Indirect Prompt Injection (Category 8) as it purposefully reads and summarizes AI instruction files (CLAUDE.md, AGENTS.md, GEMINI.md) from the target repository. Ingestion points: Instruction files identified in SKILL.md. Boundary markers: Absent. Capability inventory: Bash subprocess calls and GitHub API network operations. Sanitization: Absent.
Audit Metadata