skills/ruvnet/ruflo/safety-scan/Gen Agent Trust Hub

safety-scan

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a security utility, providing instructions on how to use AIDefence tools to scan and analyze input for malicious patterns. The tools referenced (aidefence_*) are vendor resources associated with the author.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted input. 1. Ingestion points: input-text argument in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Bash tool listed in frontmatter. 4. Sanitization: Present via the aidefence scanning tools. This is considered safe as it is the primary defensive purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 10:47 PM
Security Audit — agent-trust-hub — safety-scan