igrantio-credential-schema-qesac

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md describes static, first-party credential schema content and directs the workflow to fetch a registry schema from fixed GitHub URLs (credentialSchemas/claimPathPointer/qesac), not arbitrary outsider-authored free text submitted into a queue/feed or inbox/chat.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly tells the user to "Fetch the source before you rely on a claim path" and points to the registry URLs https://github.com/decentralised-dataexchange/verifiable-data-registry/tree/main/credentialSchemas/claimPathPointer/qesac and https://raw.githubusercontent.com/decentralised-dataexchange/verifiable-data-registry/main/credentialSchemas/claimPathPointer/qesac/2025.7.1/dc+sd-jwt.schema.json, which would be fetched at runtime and directly control the agent's claim/path handling.