monday-com

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask the user for their Monday.com API token and to insert it into configuration files or environment variables (e.g., JSON with "MONDAY_TOKEN" or .env entries), which requires the LLM to handle and potentially output the secret verbatim.

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md and referenced files (e.g., references/graphql-examples.md and scripts/monday_api.sh) explicitly instruct the agent to query Monday.com's API (https://api.monday.com/v2) to fetch board schemas, items, updates/comments and other user-generated workspace content, which the agent must read and interpret to choose actions (e.g., map column IDs, decide mutations), exposing it to untrusted third-party content that could carry indirect prompt-injection payloads.