narrative-therapy

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill provides structured instructions and guidelines for an AI to act as a Narrative Therapist. It focuses on techniques like externalization and re-authoring without any patterns of behavior-override or safety-filter bypass.
  • [DATA_EXFILTRATION]: No network operations, hardcoded credentials, or access to sensitive file paths were detected. The skill operates purely within the provided conversational context.
  • [REMOTE_CODE_EXECUTION]: The skill does not download external scripts, install packages, or execute remote commands. The external links provided in the references section are for informational purposes only.
  • [OBFUSCATION]: Analysis of the skill body and referenced files revealed no obfuscated content, encoded strings, or hidden Unicode characters.
  • [COMMAND_EXECUTION]: The skill does not use shell commands, subprocesses, or dynamic context injection patterns. The frontmatter limits the agent to standard Read, Write, and Skill tools.
  • [EXTERNAL_DOWNLOADS]: The skill references established professional organizations for psychotherapy (Dulwich Centre and Narrative Practices Adelaide). These are documented neutrally as educational resources and do not involve automated code retrieval.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 03:12 PM