etherscan-flow

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md Step 0C-0 (“Document / link” import) allows the user to supply arbitrary free text via user-typed URLs (gists/tweets/news/blog/forum) which the skill GETs once and then parses into a claim queue for runtime validation, exposing the agent to outsider-authored text that could indirectly steer behavior.