to-issues
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from an external issue tracker and uses it to generate new content and actions.
- Ingestion points: The skill reads the full body and all comments from issue references, URLs, or paths provided by the user in Step 1.
- Boundary markers: There are no explicit boundary markers or instructions to the agent to disregard potential instructions embedded within the fetched issue content.
- Capability inventory: The skill has the capability to explore the codebase (Step 2) and publish multiple new issues to the project's issue tracker (Step 5).
- Sanitization: The instructions do not include any steps to sanitize, escape, or validate the content of the comments and bodies retrieved from the external tracker before they are used to draft the task breakdown.
Audit Metadata