github-labels-query

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches repository label data from the official GitHub REST API via the gh command-line tool. This is a standard operation for repository management and targets a well-known service.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data (label names, colors, and descriptions) from potentially untrusted external repositories.
  • Ingestion points: Data enters via the gh api command in query-labels.sh.
  • Boundary markers: The skill does not use specific delimiters to isolate label content from agent instructions.
  • Capability inventory: The skill uses gh api for network requests and jq for data transformation.
  • Sanitization: The output is structured as JSON, but the text content of the labels is not sanitized for potential natural language instructions. However, the risk is inherent to tools processing external metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 07:07 PM
Security Audit — agent-trust-hub — github-labels-query