to-issues
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content from issue trackers (issue bodies and comments), which represents a potential attack surface where malicious instructions could be embedded in the data.
- Ingestion points: The skill explicitly instructs the agent to fetch issue references (numbers, URLs, or paths) and read their full body and comments (SKILL.md, Step 1).
- Capability inventory: The agent has the capability to explore the local codebase (Step 2) and publish new issues back to the issue tracker (Step 5).
- Boundary markers: No specific boundary markers, delimiters, or 'ignore instructions' warnings are defined in the skill to wrap the external data.
- Sanitization: There is no evidence of content sanitization, filtering, or validation for the fetched issue data before it is processed by the model.
Audit Metadata