The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the ams command-line interface to perform geographic queries such as geocoding, coordinate search, and routing. These commands are integral to the skill's stated purpose.
[CREDENTIALS_UNSAFE]: The skill documentation includes instructions for setting an authentication token using the AMS_TOKEN environment variable or the ams auth set-token command. It correctly uses placeholders for sensitive values and does not expose actual credentials.
[PROMPT_INJECTION]: This skill possesses an indirect prompt injection surface. Ingestion points: External data enters the context via ams command outputs. Boundary markers: Absent. Capability inventory: The skill uses subprocess calls to execute the ams command. Sanitization: Absent.

ams-cli