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: 0.90). The skill explicitly navigates and reads public LinkedIn pages and search/hashtag results (see references/research.md Step 3: navigate to https://www.linkedin.com/feed/, search results pages, and use read_page/get_page_text) and then drafts and posts comments or other actions based on that content (references/engage.md), so untrusted user-generated third-party content can influence agent behavior.
Audit Metadata