qa
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the GitHub CLI (gh issue create) to submit issues to remote repositories and performs local filesystem writes to create issue drafts in the ./issues/ directory.
- [DATA_EXFILTRATION]: The skill transmits information derived from the codebase and user input to GitHub. It attempts to mitigate accidental data exposure by instructing the agent to omit file paths, line numbers, and internal implementation details from the issue bodies.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from both the user and the local codebase files to generate its output. 1. Ingestion points: User conversation and local source code files (e.g., UBIQUITOUS_LANGUAGE.md). 2. Boundary markers: None. 3. Capability inventory: GitHub CLI issue creation and local filesystem write operations. 4. Sanitization: The skill instructs the agent to focus on user-facing behaviors and project-specific domain language while explicitly forbidding the inclusion of internal code specifics.
Audit Metadata