copywriting
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of markdown instructions for the AI's behavior. It does not include scripts, package manifests, or system commands.
- [PROMPT_INJECTION] (SAFE): No patterns of instruction override, jailbreaking, or system prompt extraction were detected. The skill uses instructional language to enforce honesty and alignment (e.g., 'You may not fabricate claims').
- [DATA_EXFILTRATION] (SAFE): No sensitive file paths, hardcoded credentials, or network transmission commands (curl, wget, fetch) are present.
- [EXTERNAL_DOWNLOADS] (SAFE): The skill does not reference or download any external scripts, packages, or binary files.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to ingest untrusted user data in Phase 1 (context gathering). While it lacks explicit boundary markers or sanitization for this input, it also lacks any exploitable capabilities (no code execution, no file writes, no network access), rendering the risk negligible.
Audit Metadata