skills/withqwerty/nutmeg/providers/Gen Agent Trust Hub

providers

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill's operations are confined to documentation search and comparison using specific MCP tools, which is consistent with its stated purpose.- [PROMPT_INJECTION]: The skill exhibits a standard architectural surface for indirect prompt injection as it processes data from external football documentation sources.
  • Ingestion points: External documentation retrieved via the mcp__football-docs__search_docs tool and the local personalization file .nutmeg.user.md.
  • Boundary markers: None present in the instructions to delimit external data.
  • Capability inventory: The skill is limited to reading files and searching documentation; it lacks tools for shell execution, file system modification, or network exfiltration.
  • Sanitization: No sanitization or validation of the retrieved documentation is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 03:43 PM