to-issues

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingest untrusted data by reading existing issues and comments from a tracker to generate new tasks. This is a standard risk for project management tools where external content could influence agent planning.
  • Ingestion points: Issue tracker bodies and comments (fetched in Step 1).
  • Boundary markers: Absent. The skill does not specify the use of delimiters when processing external content.
  • Capability inventory: Read access to the codebase; Read/Write access to the issue tracker via gh api.
  • Sanitization: None described in the instructions.
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh api) to publish issues and explore the codebase. These operations are restricted to the project's own repository and issue tracker, aligning with legitimate developer workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 12:41 PM
Security Audit — agent-trust-hub — to-issues