content-creative
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources such as Notion and an Idea Pool database, which are potentially user-controlled and could contain malicious instructions.
- Ingestion points: Idea Pool card details (hook, notes, source link) and Notion strategy documents (voice, signature, facts).
- Boundary markers: Not present; the skill lacks instructions to delimit or ignore instructions within external data.
- Capability inventory: File creation (PNG/PDF), interaction with Notion, and routing to other agent skills.
- Sanitization: No validation or sanitization steps are defined for the data retrieved from external sources.
- [COMMAND_EXECUTION]: Visual asset rendering is performed using 'headless Chrome,' which involves the execution of browser processes to generate PNG and PDF files.
- [EXTERNAL_DOWNLOADS]: The skill retrieves brand strategies and factual information from Notion, an external service, which constitutes a remote data dependency.
Audit Metadata