content-ideas-generator
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill possesses a vulnerability surface for indirect prompt injection by ingesting untrusted data and having file-writing capabilities.\n- Ingestion points: Untrusted data enters the agent context in
SKILL.md(Step 1) via user-provided text and URLs fetched through theweb_fetchtool.\n- Boundary markers: No delimiters or 'ignore embedded instructions' warnings are present to isolate user-provided content from the system logic.\n- Capability inventory: The skill performs network reads (web_fetch) and writes generated outlines to thecontent-ideas/local directory.\n- Sanitization: No escaping, validation, or filtering of external content is performed before processing.
Audit Metadata