content-repurpose
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external LinkedIn posts, creating a surface for indirect prompt injection.
- Ingestion points: The skill retrieves post data from external profiles using the
apimaestro/linkedin-profile-poststool as described inSKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to separate the scraped post content from the agent's internal instructions.
- Capability inventory: The skill has the capability to write to the 'Idea Pool' (an external data store) and generate HTML visualizations via a
visualizetool. - Sanitization: The instructions do not specify any validation or sanitization of the scraped text before it is used for idea generation.
- [EXTERNAL_DOWNLOADS]: The skill fetches data from an external platform to perform its core function.
- The skill utilizes the Apify platform (specifically the
apimaestro/linkedin-profile-postsactor) to retrieve content from LinkedIn profile pages.
Audit Metadata