ctf-reverse

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs fetching and parsing open third-party content (e.g., git clone https://github.com/zrax/pycdc in SKILL.md, using dogbolt.org for decompiler comparison, and a curl to assetdelivery.roblox.com in languages-platforms.md) so the agent is expected to ingest untrusted/user-generated web data that can materially influence analysis and follow-up actions.