issue-management

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gh (GitHub CLI) tool for all operations. The commands provided are standard for GitHub's Issues 2.0 implementation and are used as intended by the tool's design.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as issue titles, bodies, and numbers which are then passed to the GitHub API. While this creates a surface for indirect prompt injection, the skill specifically recommends best practices to mitigate risks.
  • Ingestion points: External data from GitHub issues or local files used to populate issue fields in SKILL.md.
  • Boundary markers: Not explicitly defined for the LLM context, but the skill relies on CLI flags for data separation.
  • Capability inventory: Accesses remote repositories via gh issue commands (create, edit, view).
  • Sanitization: Recommends using the --body-file flag to handle issue content, which prevents data from being misinterpreted as shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 06:47 PM