ai-codebase-review
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the bash tool to execute shell commands for repository analysis and vault management, including git rev-parse, date, and the sequence git add, git commit, and git push.
- [DATA_EXFILTRATION]: The skill includes functionality to push local files from the user's Obsidian vault to a remote Git repository using git push for synchronization.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the analysis of untrusted codebase content. 1. Ingestion points: The skill reads the entire codebase, including request entrypoints and application logic. 2. Boundary markers: None identified; there are no instructions to distinguish between the skill's directives and the content of analyzed files. 3. Capability inventory: The skill has filesystem access (Read, Write, Edit) and shell execution capabilities (bash, git). 4. Sanitization: None described for codebase content before processing.
Audit Metadata