content-creator
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or remote code execution detected. The skill's operations are limited to reading local reference files and writing generated drafts to a local directory.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted user themes and reads data from potentially external context files.
- Ingestion points: User-provided prompts and the
marketing/product-context.mdfile. - Boundary markers: Absent. The instructions do not provide delimiters to separate instruction from data.
- Capability inventory: File system access (read/write) for markdown content. No network or code execution capabilities.
- Sanitization: Absent. The skill does not describe any validation or filtering of input data.
Audit Metadata