diagnose-ssr

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes content from arbitrary URLs.
  • Ingestion points: Data enters via agent-browser snapshot and agent-browser get text body in SKILL.md.
  • Boundary markers: Lacks explicit delimiters or warnings for the agent to disregard instructions found within the processed content.
  • Capability inventory: Uses agent-browser for network routing, navigation, and data extraction.
  • Sanitization: No filtering or validation of external webpage content is performed before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 08:26 PM
Security Audit — agent-trust-hub — diagnose-ssr