rdd-defect-workflow
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of external repository data.
- Ingestion points: The skill processes content from repository issues and pull requests (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious commands embedded within issue descriptions or pull request comments.
- Capability inventory: The skill utilizes file system access for worktree isolation, code mapping via CodeGraph, and local test execution (Execution Steps 2-4).
- Sanitization: No sanitization or validation logic is specified for the external data retrieved from the repository.
Audit Metadata