skill-oracle

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md Step 3 instructs the agent to curl the public ClawHub API (https://clawhub.ai/api/search?q=...) and parse/print the returned 'summary' and 'slug' fields, which are untrusted third‑party registry entries that the agent reads and can use to decide installs and follow-up actions.