linkedin-post-generator

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and references/source-integrations.md explicitly instruct the agent to fetch and ingest user-generated content from external sources—e.g., LinkedIn posts via the apify-scrapers script in the style-setup flow and auto-pulling transcripts/docs from Fireflies.ai, Slack, and Google Drive during the --refresh flow—which the agent reads and uses to shape generated posts, creating a clear path for untrusted third-party content to influence behavior.