people-search

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

• Third-party content exposure detected (low risk: 0.10). The skill workflow involves searching and fetching arbitrary web pages via lessie web-search and lessie web-fetch, which ingest outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to execute a curl command fetching remote skill material from https://raw.githubusercontent.com/LessieAI/lessie-skill/main/people-search/SKILL.md (which lacks independent authentication and points to an arbitrary third-party/community repository), constituting an unverifiable runtime external dependency under weak/unknown provenance.