skills/sehoon787/my-codex/browser-qa/Gen Agent Trust Hub

browser-qa

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it is designed to ingest and act upon data from untrusted external web pages. An attacker could embed malicious instructions within a target site to manipulate the testing logic or interaction flow.
  • Ingestion points: Untrusted content from target URLs is processed during navigation and interaction phases (SKILL.md).
  • Boundary markers: No delimiters or "ignore instructions" warnings are defined to separate the webpage content from the agent's core instructions.
  • Capability inventory: Includes powerful browser automation capabilities such as clicking, form submission, and authentication testing (SKILL.md).
  • Sanitization: No sanitization or validation of the ingested webpage content is specified before the agent performs actions based on it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 07:41 AM
Security Audit — agent-trust-hub — browser-qa