web-js-reverse-master-flow

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to analyze and process data from external, untrusted web pages and JavaScript code.
  • Ingestion points: The skill takes a URL, target request data, cookies, and messages from external websites as primary inputs in the 'Input Block' section.
  • Boundary markers: There are no explicit instructions or delimiters provided to the agent to distinguish between its own operational instructions and potentially malicious instructions embedded in the target website's code or responses.
  • Capability inventory: The agent is authorized to use multiple MCPs (chrome-devtools-mcp, js-reverse, jshook) that allow it to execute commands, interact with live browser sessions, and write analysis records to the local file system (e.g., in the 'reverse-records/' directory).
  • Sanitization: The instructions do not define any sanitization or validation protocols for the external content before it is processed by the agent or stored in records.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 07:09 PM
Security Audit — agent-trust-hub — web-js-reverse-master-flow