skills/clawic/skills/Design/Gen Agent Trust Hub

Design

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses an auto-adaptive mechanism to update its own instructions in SKILL.md based on user feedback, which creates a surface for indirect prompt injection. Ingestion points: User choices and feedback are used to modify SKILL.md. Boundary markers: Absent in SKILL.md placeholders. Capability inventory: Modifies its own SKILL.md file. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 10:44 AM
Security Audit — agent-trust-hub — Design