to-issues
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill reads project documentation, ADRs, and codebase context to publish issues to external project trackers. This information flow is consistent with the skill's primary function of issue management.\n- [PROMPT_INJECTION]: The process involves reading external data from issue trackers which presents a surface for indirect prompt injection.\n
- Ingestion points: Fetches issue body and comments from external issue trackers in the 'Gather context' step (SKILL.md).\n
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands for the external content.\n
- Capability inventory: The skill has codebase read access and issue publication capabilities.\n
- Sanitization: External content is used directly for drafting vertical slices without explicit sanitization steps.
Audit Metadata