to-issues

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads content from external issue trackers which could potentially contain malicious instructions (e.g., in issue bodies or comments). However, the skill implements a mandatory human-in-the-loop checkpoint by requiring user confirmation of the proposed breakdown before any issues are published, effectively mitigating the risk of indirect injection.
  • Ingestion points: Fetches issue bodies and comments from an issue tracker based on user-provided references (SKILL.md, Step 1).
  • Boundary markers: No explicit delimiters or instructions are specified to isolate fetched external content from the agent's instructions.
  • Capability inventory: Performs codebase exploration (file system read) and interacts with an issue tracker API (network/API read and write operations).
  • Sanitization: No explicit sanitization or validation of the fetched issue content is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 10:27 AM
Security Audit — agent-trust-hub — to-issues