browse-ai

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the vendor's own command-line interface, @membranehq/cli, to manage authentication and execute actions. This is consistent with the stated purpose of the skill and the author's identity.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and process unstructured data from external websites via Browse AI.
  • Ingestion points: Data is received into the agent context through membrane action run and membrane request commands, particularly when retrieving results from scraping tasks.
  • Boundary markers: The instructions do not define specific delimiters or instructions to the agent to ignore embedded commands in the scraped content.
  • Capability inventory: The skill allows the agent to execute shell commands via the membrane CLI and make network requests through the Membrane proxy.
  • Sanitization: There is no explicit evidence of content sanitization or filtering mentioned in the SKILL.md documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 09:38 PM
Security Audit — agent-trust-hub — browse-ai