hunt-jwt-crypto
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use various security tools for token analysis and exploitation. Evidence: Use of jwt_tool, hashcat, and nuclei.
- [DYNAMIC_EXECUTION]: Shell commands are dynamically generated using input from the target application. Evidence: Commands like jwt_tool and nuclei -u <target_url> interpolate external variables into subprocess calls.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted JWTs from target servers, creating an attack surface. Ingestion points: Reads tokens from Authorization headers, cookies, and login responses. Boundary markers: No explicit delimiters are used to sanitize or isolate the token data. Capability inventory: Includes network operations and system command execution via third-party tools. Sanitization: The instructions do not define validation or filtering logic for the ingested tokens.
Audit Metadata