find-skills

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

• Third-party content exposure detected (high risk: 0.80). This skill's workflow and scripts (see SKILL.md and scripts/enrich_find.js / references/enriched-search.md) explicitly fetch and parse descriptions from the public skills.sh pages (with fallback to agent-skills.md) and then use those third-party descriptions to present and guide install decisions, exposing the agent to untrusted web content that could contain indirect instructions.