notion

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks the user to paste their Notion integration token into the conversation and then shows a command that embeds that token verbatim as a command-line argument (ruby .../save_token.rb 'PASTED_TOKEN'), which requires the LLM to receive and potentially output the secret directly.

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

• Third-party content exposure detected (high risk: 0.80). This skill fetches and parses user-generated Notion content from the Notion API (e.g., scripts/search.rb, scripts/pages.rb, scripts/blocks.rb calling https://api.notion.com/v1) and uses that page/block text to present results and drive subsequent actions (create/update/append/delete), so untrusted third‑party content could indirectly inject instructions into the agent's workflow.