snap-ship
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its workflow of ingesting external, untrusted data to generate Pull Request content.
- Ingestion points: In
SKILL.md, the workflow retrieves data from "linked issue body + comments and material parent PRD/epic/breakdown links" during the analysis phase. - Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore instructions embedded within the fetched external data.
- Capability inventory: The skill utilizes the GitHub environment to create and update Pull Requests, which involves writing data to the repository's metadata and conversation history.
- Sanitization: There is no mention of sanitizing or escaping the retrieved content before it is processed by the model to generate the final PR title and body.
Audit Metadata