triage
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external GitHub issues and pull requests which can contain malicious instructions.
- Ingestion points: Step 1 of the triage process in
SKILL.mdreads issue bodies, comments, and pull request diffs. - Boundary markers: Absent. The instructions do not include specific delimiters or warnings to ignore instructions found within the issue data.
- Capability inventory: Step 3 in
SKILL.mdinstructs the agent to "run the relevant tests or commands" to verify bug reports. - Sanitization: Absent. The skill does not describe any validation or escaping of external content.
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands or run tests as part of the triage verification workflow.
- Evidence:
SKILL.mdexplicitly tells the agent to "reproduce it from the reporter's steps" and "run the relevant tests or commands" for pull requests. This capability is exposed to untrusted input from the issue tracker.
Audit Metadata