detect-support-requests

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user content from feature request titles and descriptions. \n
  • Ingestion points: Step 2 fetches data via the wccom-feature-requests-list tool or from a provided input_path. \n
  • Boundary markers: None defined to isolate instructions from the processed data. \n
  • Capability inventory: The skill can post comments (wccom-feature-requests-comment) and change request statuses (wccom-feature-requests-update-status). \n
  • Sanitization: No input sanitization is performed. \n
  • Mitigation: Mandatory manual user approval in Step 5 and Step 6 effectively prevents the autonomous execution of potentially malicious instructions embedded in the requests. \n- [SAFE]: All tool calls and external URL references relate directly to official WooCommerce infrastructure, matching the author's identity and expected skill purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 03:47 AM
Security Audit — agent-trust-hub — detect-support-requests