web-research-assistant

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface detected. Ingestion point: scripts/research.py fetches untrusted search result snippets and titles from an external API. Boundary markers: No delimiters are used to wrap external content or warn the agent to ignore instructions within the data. Capability inventory: The skill can write reports to the local file system and perform network requests to the vendor API. Sanitization: No filtering or escaping of retrieved web content is performed.
  • [DATA_EXFILTRATION]: The skill performs network operations targeting mcp.browseract.com. This is a vendor-owned domain associated with the skill author 'browser-act' and is part of the intended search functionality. No sensitive local data or credentials were found to be exfiltrated.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 07:59 AM