Skills
skills/mitodl/agent-kit/create-github-issue/Gen Agent Trust Hub

create-github-issue

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-provided content (issue titles, bodies, and repository names) and includes it in tool calls and templates.
  • Ingestion points: User input for the repository, issue type, title, and body details defined in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions to ignore instructions embedded within user-provided strings.
  • Capability inventory: The skill uses the gh issue create command to interact with GitHub.
  • Sanitization: The skill suggests stripping HTML comments but lacks comprehensive sanitization or shell escaping for the interpolated user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 05:28 PM