find-skills

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

• Third-party content exposure detected (low risk: 0.10). The agent searches and browses skills from the public ecosystem via skills.sh, where an outsider can publish skills containing arbitrary free text ingested during search and validation.

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 run third-party packages via npx skills add from an unspecified ecosystem, which constitutes an unverified runtime dependency.