ray-metrics

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill retrieves account metadata and performance metrics (impressions, likes, retweets, etc.) via X API tools. This data access is documented and required for the primary function of generating reports.
  • [PROMPT_INJECTION]: The skill analyzes untrusted external data, which creates a surface for indirect prompt injection.
  • Ingestion points: External content is ingested via the text of retrieved tweets and through user-uploaded CSV files provided during fallback procedures.
  • Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when it processes the retrieved tweet text for categorization.
  • Capability inventory: The skill lacks dangerous capabilities such as arbitrary shell execution, system modification, or network requests to unknown domains; it is limited to the xapi toolset and text formatting.
  • Sanitization: No explicit sanitization or validation of the tweet text content is described before the agent performs attribution and content analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:42 AM
Security Audit — agent-trust-hub — ray-metrics