guided-launch-announcement
Warn
Audited by Snyk on Feb 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly asks for a public marketing URL (STEP 1) and then mandates fetching and extracting brand signals from the live site (STEP 3), meaning untrusted third‑party web content will be read and used to drive design decisions and actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches and analyzes a user-provided URL (the site URL supplied in STEP 1) at runtime to extract brand signals that directly drive the agent's prompts and creative specification, so the user-provided URL is a runtime external dependency that controls agent behavior.
Audit Metadata