onequery-bug

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted data from GitHub issues.
  • Ingestion points: Fetches issue bodies and user comments from api.github.com/repos/wordbricks/onequery/issues/.
  • Boundary markers: Missing. There are no instructions to use delimiters or treat the fetched data as untrusted content separate from system instructions.
  • Capability inventory: The agent has the ability to perform network requests and inspect local repository files.
  • Sanitization: No validation or sanitization of the fetched issue content is performed before processing.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch bug report data.
  • Context: Accesses the GitHub API to retrieve details from the official repository of the skill's author.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 04:46 AM
Security Audit — agent-trust-hub — onequery-bug