yara-sigs

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly clones the public GitHub repository https://github.com/x64dbg/yarasigs in SKILL.md step 2 and the yara_scan.py script then loads and compiles YARA rule files from that yarasigs directory (including rule metadata and match results) which the agent reads and uses to generate findings, meaning arbitrary third‑party rule content can influence scan decisions and reporting.