The Agent Skills Directory

[SAFE]: The skill interacts with the official Monday.com API endpoint at api.monday.com. This is a well-known service and the usage matches the skill's stated purpose.- [COMMAND_EXECUTION]: The skill utilizes curl commands to perform board and item management tasks on Monday.com. This is the primary intended functionality and does not involve unauthorized system modifications.- [DATA_EXFILTRATION]: Network activity is restricted to the authorized API provider. There is no evidence of the skill attempting to access sensitive local files, such as SSH keys or AWS credentials, for exfiltration.- [PROMPT_INJECTION]: The instructions are focused on providing API examples and do not contain any patterns intended to bypass agent safety filters or override core instructions.- [PROMPT_INJECTION]: Surface for indirect prompt injection exists as the skill processes data from an external API (Monday.com). Ingestion points: JSON responses from curl calls in SKILL.md. Boundary markers: Absent. Capability inventory: Command execution via curl. Sanitization: Absent. Given this is a standard API integration for a well-known service, the risk is considered baseline for this type of tool.

monday