issue-triage
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection because it reads and processes untrusted data from a project codebase to generate GitHub issue content.\n
- Ingestion points: The skill uses sub-agents to read code files and functions to gather context for the issue body.\n
- Boundary markers: The skill requires an explicit user confirmation ("wait for a yes") after displaying the target repository visibility, issue title, and body text.\n
- Capability inventory: The skill executes the
gh issue createcommand to submit content to external GitHub repositories.\n - Sanitization: There is no explicit sanitization or escaping of the codebase content before it is summarized and placed into the issue template.
Audit Metadata