github-create-label

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is potentially vulnerable to indirect prompt injection because it processes user-provided label names and descriptions without explicit sanitization or boundary markers before passing them to tools.
  • Ingestion points: User-defined 'name' and 'description' parameters in SKILL.md.
  • Boundary markers: Absent; no delimiters are used to separate untrusted user content from the tool instructions.
  • Capability inventory: Execution of GitHub CLI (gh) commands and GitHub REST API network requests.
  • Sanitization: No sanitization, escaping, or validation of user input is described in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 04:56 PM