linkedin-repurposing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt tells users to inject their API key directly into a shell command (COLDIQ_API_KEY= npx ...), which requires placing the secret on the command line where it can be exposed in process listings or shell history—an insecure credential-handling pattern.

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

• Third-party content exposure detected (high risk: 0.70). The skill instructs runtime extraction of engagement and signals from ColdIQ using the user/competitor’s LinkedIn posts via an MCP/API call (“mcp__coldiq__extract_post_engagement”, “mcp__coldiq__find_signals”), which can cause outsider-authored post text to be ingested into the LLM context.