hunt-schema-enumeration

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill includes plaintext API-token examples (ANON_KEY="eyJ...") and constructs curl commands that place API keys/Bearer tokens directly in headers (e.g., -H "apikey: ${ANON_KEY}" / -H "Authorization: Bearer ${ANON_KEY}"), which encourages embedding secrets into generated commands and could force the LLM to handle or reproduce secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document provides explicit, actionable offensive techniques for API schema enumeration and follow-on exploitation (fuzzing, write-testing, JWT attacks), indicating clear malicious intent and high risk of abuse.

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

• Third-party content exposure detected (low risk: 0.10). The runtime workflow described in SKILL.md performs schema enumeration by sending crafted REST/GraphQL requests and ingesting the resulting JSON validation/error responses from the target API, which are outsider-influenced only insofar as they come back from the target (not from a direct outsider-authored free-text source within the workflow).