skills/ulpi-io/skills/browse-aeo/Gen Agent Trust Hub

browse-aeo

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the browse command-line tool via Bash to navigate to URLs and extract document structure, metadata, and text. These operations are essential to the skill's primary function of performing website audits.
  • [INDIRECT_PROMPT_INJECTION]: By fetching and analyzing text from user-provided external URLs, the skill is exposed to indirect prompt injection. Attackers could place hidden malicious instructions within a page's content or metadata that attempt to influence the agent's reasoning or behavior during the analysis process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:56 PM
Security Audit — agent-trust-hub — browse-aeo