research

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill's behavior matches its stated purpose of documentation research.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites via WebFetch and WebSearch, which is a common surface for indirect prompt injection. The skill lacks explicit boundary markers or instructions to ignore embedded commands in the fetched content, though this is a standard risk for web-based research tools.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill utilizes Memory MCP to store findings. There are no patterns suggesting the exfiltration of sensitive local data or hardcoded credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:46 AM
Security Audit — agent-trust-hub — research