Skills
skills/openrouterteam/skills/openrouter-images/Gen Agent Trust Hub

openrouter-images

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses the OPENROUTER_API_KEY from the environment to authenticate requests to the OpenRouter service.
  • [DATA_EXFILTRATION]: Network communication is established with https://openrouter.ai/api/v1/chat/completions to transmit prompts and image data.
  • [PROMPT_INJECTION]: The skill processes external, untrusted data which creates a surface for indirect prompt injection attacks.
  • Ingestion points: User-supplied text prompts and local image files are ingested as input in generate.ts and edit.ts.
  • Boundary markers: No delimiters or specific instructions are provided to the model to ignore potentially malicious instructions embedded in the user input.
  • Capability inventory: The skill possesses file-writing capabilities through the saveImage function in lib.ts, which uses writeFileSync to save generated content.
  • Sanitization: Input prompts and image data are sent to the API without validation or escaping of special characters or instruction sequences.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 04:59 PM