linkedin-growth

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly tells the agent to ask the user for API tokens and then embed them verbatim into a command-line invocation (linkedin setup --linked-api-token=<a> --identification-token=<b>), which requires the LLM to handle and output secret values directly.

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

• Third-party content exposure detected (high risk: 0.75). The required runtime flow for Phase A qualification instructs the agent to pass candidate lead fields (sourced from linkedin-cli search results, i.e., scraped/outsider-authored profile text) plus the qualification contract/ICP into a sub-agent/LLM for classification, so outsider free text reaches LLM context via the candidate/result “qualify” path.