what-i-did
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gh(GitHub CLI) tool to perform multiple API queries, including identifying the current user, fetching event logs, and searching for commits and pull requests across multiple repositories. - [PROMPT_INJECTION]: The skill processes untrusted external data retrieved from GitHub (commit messages and pull request titles), which creates an inherent surface for indirect prompt injection.
- Ingestion points: Data enters the agent via
gh apiandgh searchresponses as described inSKILL.md. - Boundary markers: No specific delimiters or safety instructions are provided to the model to help it distinguish between data and instructions when summarizing the retrieved content.
- Capability inventory: The skill executes shell commands and uses the GitHub CLI to interact with remote services.
- Sanitization: The skill does not perform sanitization or filtering on the text content of commits or pull requests before they are processed by the agent.
Audit Metadata