gate-info-liveroomlocation

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs HTTP GET requests to the gate.io API endpoint (/live/gate_ai/tag_coin_live_replay) to retrieve metadata for live streams and videos. This is a functional requirement for the skill and targets infrastructure owned by the vendor.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of external, untrusted content.
  • Ingestion points: The agent retrieves live.name and video.title (user-generated content from stream creators) from the Gate API as specified in SKILL.md.
  • Boundary markers: The instructions do not define boundary markers (such as XML tags or delimiters) to isolate the external content or instruct the agent to ignore any commands embedded within those strings.
  • Capability inventory: The skill's primary capability is to display the retrieved titles and links as a list in the chat response.
  • Sanitization: There are no instructions provided for sanitizing or validating the retrieved titles before they are included in the output, allowing potentially malicious instructions to enter the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 04:25 PM