skills/only-cli/oc/web-browsing-cli/Gen Agent Trust Hub

web-browsing-cli

Pass

Audited by Gen Agent Trust Hub on Sep 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to execute the @only-cli/oc package, which is a vendor-owned resource.
  • [COMMAND_EXECUTION]: The skill relies on shell command execution to perform web browsing, site searches, and session state management.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted web content from arbitrary URLs, presenting a surface for indirect prompt injection.
  • Ingestion points: External web content retrieved through various extraction commands in SKILL.md.
  • Boundary markers: The documentation includes an explicit safety warning in the Untrusted content section to treat ingested text as data rather than instructions.
  • Capability inventory: Shell execution capabilities via npx and local filesystem access for session storage in ~/.only-cli/sessions/.
  • Sanitization: The tool converts complex HTML into a simplified, token-efficient terminal format, which helps reduce injection surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 27, 2026, 10:24 PM
Security Audit — agent-trust-hub — web-browsing-cli