content

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the model to fetch and verbatim-copy source content (including Gmail threads, PDFs, pasted text, or web pages) into final posts, so if those sources contain API keys, tokens, or passwords the agent would reproduce them in output, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 1 explicitly instructs fetching arbitrary URLs with "use web_fetch to retrieve the full page content" and to fetch emails/newsletters from Gmail, and Steps 2–4 require reading and using that third-party content to draft and act on LinkedIn posts, so untrusted web or user-generated content can be ingested and materially influence the agent's outputs.