testing-jwt-token-security

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The required workflow performs active fetching of JWKS endpoints and target URLs specified by the user, representing low-risk indirect prompt injection exposure via arbitrary web requests.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains an explicit remote-repository locator for jwt_tool (https://github.com/ticarpi/jwt_tool.git) in its documentation and usage instructions, which is cloned or installed at runtime as an operational tool dependency under an unofficial, community-owned repository (medium provenance).