alterlab-yokatlas

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime path calls scripts/yokatlas_lookup.py, which uses the keyless yokatlas-py wrapper to fetch JSON from YÖK Atlas endpoints (/api/tercih-kilavuz/universiteler, /search, /program); this is outsider-authored public web content that becomes readable text/JSON in the agent’s LLM context.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)