linkedin-analytics

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly shows and instructs embedding API keys directly into configuration and curl headers (e.g., "Authorization: Bearer YOUR_API_KEY" and "x-publora-key: sk_your_api_key"), which would require the LLM to include secret values verbatim in generated output.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch LinkedIn data via the Publora MCP/REST API (e.g., https://api.publora.com/api/v1/linkedin-post-statistics and /linkedin-account-statistics in SKILL.md), which ingests user-generated social media content/metrics from a third-party service that the agent must read and act on (analysis, recommendations, reacting/commenting), creating a clear avenue for indirect prompt injection.