ralph-it
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external GitHub sources which presents a potential injection surface.
- Ingestion points: The skill fetches PRD issue content and merged PR bodies/comments using the
ghCLI as described in Step 1. - Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the fetched GitHub content as data only or to ignore embedded instructions.
- Capability inventory: The skill possesses the ability to perform network operations via the
ghCLI (Step 1, 5), write files during implementation (Step 4), and execute shell commands for testing and typechecking (Step 4). - Sanitization: The instructions do not include any steps for sanitizing, filtering, or validating the content retrieved from GitHub before it is used to recommend the next user story or propose an implementation plan.
Audit Metadata