trauma-informed-practice-designer

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides instructional guidance and does not perform any sensitive operations, such as network requests or file access. The author GarethManning appears to have provided a legitimate educational tool.- [NO_CODE]: No scripts or binaries are present in the skill; all logic is defined in a markdown prompt template.- [PROMPT_INJECTION]: The skill processes untrusted user data via input schema variables. 1. Ingestion points: Variable interpolation (e.g., {{classroom_situation}}) in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: No tools, scripts, or system permissions available to the skill. 4. Sanitization: Not present. Because no capabilities or sensitive data are exposed, the risk of injection is restricted to output text modification and is considered safe.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 03:33 PM
Security Audit — agent-trust-hub — trauma-informed-practice-designer