07-repurpose
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content fetched from external LinkedIn profiles and Notion strategy documents, which introduces a surface for instructions embedded within that data to influence agent behavior.
- Ingestion points: The skill retrieves LinkedIn post data via Apify and strategy information from Notion files.
- Boundary markers: There are no explicit delimiters or specific instructions for the agent to treat the fetched post content as untrusted data or to ignore potential instructions embedded within the posts.
- Capability inventory: The skill performs read operations on local reference files, makes external API calls via Apify, writes ideas to a storage location (Idea Pool), and generates HTML-based visualizations.
- Sanitization: No explicit sanitization or filtering logic is defined for the external content before it is processed or displayed in the visualization widget.
Audit Metadata