skills/addfox/skills/addfox-debugging/Gen Agent Trust Hub

addfox-debugging

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed to diagnose framework-specific issues by reading local project files such as .addfox/error.md and .addfox/meta.md. These operations are standard for development troubleshooting.
  • [SAFE]: The skill suggests using the addfox CLI and the Rsdoctor tool. These are recognized resources within the vendor's development ecosystem.
  • [PROMPT_INJECTION]: The skill ingests data from local error logs which presents a surface for indirect prompt injection. 1. Ingestion points: .addfox/error.md. 2. Boundary markers: Absent. 3. Capability inventory: CLI execution and file writes. 4. Sanitization: Absent. This is a standard risk for debugging tools and is considered safe in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 03:13 AM