architecture-audit
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data from the codebase being audited and has access to high-capability tools like Bash and Agent. 1. Ingestion points: File reading via Read, Grep, and Glob tools. 2. Boundary markers: None specified to delimit or ignore instructions within audited files. 3. Capability inventory: Uses Bash to create GitHub issues and the Agent tool to spawn sub-agents. 4. Sanitization: No sanitization or validation of the content read from the codebase is performed before it is used to drive agent actions.
- [COMMAND_EXECUTION]: The skill automatically executes shell commands using the Bash tool to interact with the GitHub CLI (gh issue create). It specifically instructs the agent not to ask for user review before creating issues, which reduces human oversight for automated external actions.
Audit Metadata