linkedin

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs extracting and reusing the LinkedIn session cookie (li_at) for API requests, which requires copying and embedding a secret value verbatim and therefore creates a high exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses the browser tool to navigate/snapshot LinkedIn pages (e.g., /messaging/, /search/results/people/, /in/USERNAME/), which will ingest outsider-authored profile/message/search text into the agent’s LLM context via rendered page content.