creative-writing
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- Prompt Injection (SAFE): No instructions to override safety filters or disregard system rules were found. The skill explicitly prioritizes safety and policy over user-provided constraints.
- Data Exposure & Exfiltration (SAFE): No access to sensitive file paths, hardcoded secrets, or network commands was identified.
- Indirect Prompt Injection (LOW): The skill processes untrusted user input for creative writing. 1. Ingestion points: User-provided writing constraints in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None (no file, network, or subprocess execution). 4. Sanitization: Present (filtering for banned words and phrases). The risk is limited to the generated text output and does not affect system integrity.
- Remote Code Execution (SAFE): No executable scripts, binary files, or remote package dependencies are present in the skill files.
Audit Metadata