improve-codebase-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from codebase files, which represents an attack surface for indirect prompt injection. \n
- Ingestion points: The skill utilizes the Agent tool with
subagent_type=Exploreto navigate and read codebase content as specified in Step 1 of SKILL.md. \n - Boundary markers: The instructions do not define delimiters or specific safety instructions to disregard embedded commands in the analyzed codebase. \n
- Capability inventory: The agent has the capability to create GitHub issues (
gh issue create) and orchestrate multiple sub-agents using theAgenttool. \n - Sanitization: No sanitization or content validation is performed on the ingested codebase data before it is processed by the agent. \n- [COMMAND_EXECUTION]: The skill leverages the GitHub CLI to programmatically create issues on the repository. \n
- Evidence: Step 7 of the Process section in SKILL.md instructs the agent to create a refactor RFC as a GitHub issue using the
gh issue createcommand. The skill directs the agent to perform this action autonomously and share the URL without requiring prior user review of the issue content.
Audit Metadata