find-skills

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow uses the Skills CLI to search/browse the open skills ecosystem (e.g., npx skills find [query] and installing from GitHub/skills.sh), which can ingest outsider-authored free text from public web/package sources into the agent’s context.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill's workflow explicitly instructs installing runtime packages with commands like "npx skills add " (e.g., vercel-labs/agent-skills@react-best-practices) and points to the skills.sh ecosystem, which will fetch and execute remote code during runtime and can supply prompts/instructions from external repositories.