skills/anentrypoint/gm-skill/browser/Gen Agent Trust Hub

browser

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to utilize a command-line utility called playwriter to manage browser sessions and execute JavaScript strings via the -e flag.
  • [COMMAND_EXECUTION]: The skill defines a mechanism for executing code by writing JavaScript snippets to a spool directory located at .gm/exec-spool/in/browser/, which are then processed by the underlying platform.
  • [PROMPT_INJECTION]: As a web-browsing skill, it possesses an attack surface for indirect prompt injection where malicious instructions embedded in visited websites could attempt to influence the agent's behavior.
  • Ingestion points: Untrusted data enters the context through page.goto, $$eval, and snapshot operations described in SKILL.md.
  • Boundary markers: No specific delimiters or warnings to ignore embedded instructions are present in the provided snippets.
  • Capability inventory: The skill has the ability to write files to the spool directory and execute arbitrary JavaScript within the browser environment.
  • Sanitization: No explicit sanitization or filtering of content extracted from web pages is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 10:31 AM
Security Audit — agent-trust-hub — browser