to-issues
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of instructional content in markdown format within the SKILL.md file. There are no accompanying scripts, binaries, or configuration files that execute code on the host system.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve reading data from an external source (issue tracker), which is an inherent part of its project management functionality.
- Ingestion points: The agent is instructed to read the full body and comments of issues from an issue tracker in Step 1.
- Boundary markers: No specific delimiters are used to wrap the ingested content, though the process relies on the agent's internal reasoning.
- Capability inventory: The skill's capabilities are limited to exploring the codebase and publishing new issues based on user approval.
- Sanitization: There is no explicit sanitization step for the ingested text, but the risk is mitigated by the requirement for human review (Step 4) before issues are published.
Audit Metadata