gemini-infographic
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured workflow to generate image prompts. It does not perform network operations, file system modifications, or command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-supplied content (Step 1) to create an infographic brief. The risk is minimized as the skill has no dangerous capabilities and includes a mandatory human-in-the-loop approval step (Step 2) before the final prompt is generated.
- Ingestion points: User-provided text content in SKILL.md Step 1.
- Boundary markers: None defined for the source text.
- Capability inventory: No shell access, network operations, or file-writing capabilities identified across the instructions.
- Sanitization: None specified; the skill relies on the agent's internal logic and user review for safety.
Audit Metadata