Fail
Audited by Snyk on Feb 25, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The prompt explicitly instructs extracting and storing the LinkedIn session cookie (li_at) for API requests, which would require the agent or user to handle and potentially embed that secret value verbatim—creating a strong exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's required workflow (SKILL.md) instructs the agent to navigate and snapshot LinkedIn pages (e.g., https://www.linkedin.com/messaging/, profiles, search results), which are public, user-generated third-party pages that the agent will read and that can materially influence actions like composing/sending messages or connection requests.
Audit Metadata