improve-codebase-architecture
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill explores and processes external codebase data, which presents an indirect prompt injection surface where malicious code comments or documentation could attempt to influence agent behavior. (1) Ingestion points: Codebase files are read using the Explore tool in SKILL.md. (2) Boundary markers: No delimiters or specific instructions are provided to ignore embedded instructions in the codebase. (3) Capability inventory: The skill utilizes the GitHub CLI (gh issue create) for write operations and can spawn sub-agents. (4) Sanitization: Input from the codebase is not sanitized or escaped before processing.
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI tool to perform automated repository modifications. Evidence: Step 7 of SKILL.md uses gh issue create to post issue content without requesting a final user review.
Audit Metadata