real-time-content
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to ingest and process untrusted external data like trends and events. Evidence: 1. Ingestion points: External trend data and current events described in SKILL.md (e.g., 'responding to trends, events, and moments'). 2. Boundary markers: No explicit instructions or delimiters are provided to the agent to ignore instructions embedded in the processed external data. 3. Capability inventory: The skill performs content generation (visuals, video, and copy). 4. Sanitization: No sanitization or validation of the ingested real-time content is mentioned in the instructions.
Audit Metadata