performance-review
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Execute tool to run git log and git config commands. These operations are used to identify contributors and the local user to scope the analysis within the repository.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes untrusted content from the repository and git logs.
- Ingestion points: Repository files (via Read and Grep) and git commit messages (via Execute).
- Boundary markers: No specific delimiters or ignore instructions markers are used when analyzing these data sources.
- Capability inventory: File system access (LS, Read, Grep), shell execution (Execute), and user interaction (AskUser).
- Sanitization: There is no explicit sanitization or filtering of the content read from files or logs before it is used to generate the final review.
- [SAFE]: The skill accesses repository file content and metadata for analysis. It includes a proactive security section instructing the agent to ignore and never read sensitive files such as .env, API keys, and private keys. It also includes a promotional link to the vendor's documentation (docs.factory.ai) and a user-triggered Twitter sharing link, which are informational and do not involve unauthorized data transmission.
Audit Metadata