cmd-fix-internal-requests
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes Git and GitHub CLI (gh) commands to perform repository operations including creating worktrees, branches, and pull requests.
- [PROMPT_INJECTION]: The skill processes external data (GitHub issue bodies) to guide its code modifications, which introduces a surface for indirect prompt injection.
- Ingestion points: Issue bodies are fetched via the gh tool or GitHub MCP as untrusted input.
- Boundary markers: No delimiters are specified to isolate issue content from the agent's core instructions.
- Capability inventory: The agent can modify source code, execute repository-specific build/test commands, and push code to remote branches.
- Sanitization: No sanitization or validation of the issue description is performed.
- Remediation: It is recommended to implement delimiters for external content and provide explicit instructions to the agent to treat issue bodies as data rather than instructions.
Audit Metadata