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 snapshotandagent-browser get text bodyin SKILL.md. - Boundary markers: Lacks explicit delimiters or warnings for the agent to disregard instructions found within the processed content.
- Capability inventory: Uses
agent-browserfor network routing, navigation, and data extraction. - Sanitization: No filtering or validation of external webpage content is performed before analysis.
Audit Metadata