content-creator
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external web sources to generate social media content and visuals.
- Ingestion points: Step 3 (Read Source Material) fetches content from user-supplied URLs or search result pages using the
browser_markdownorWebFetchtools. - Boundary markers: The skill instructions do not specify the use of delimiters, headers, or 'ignore instructions' warnings when interpolating fetched external content into the agent's context.
- Capability inventory: The skill uses the
Writetool to save files to theworkspace/directory and integrates with themcp__notebooklm__*toolset to generate visual assets from the fetched content. - Sanitization: There is no mention of sanitizing, filtering, or escaping the external source material before it is used for drafting posts or sent as source text to the NotebookLM service.
Audit Metadata