The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses subprocess calls to execute official service CLI tools (e.g., gh auth status, aws sts get-caller-identity) to verify and manage authentication status. This is the primary intended function of the skill and follows standard integration patterns for service authentication.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with external service APIs and CLI tools, creating a potential surface for indirect prompt injection if malicious service responses are processed. Ingestion points: Service status outputs and CLI responses ingested by authentication verification functions in shell and Python scripts. Boundary markers: None explicitly implemented, though the use of structured status checks reduces risk. Capability inventory: The skill has capabilities to execute shell commands via subprocess.run and write to the local file system (cache directory). Sanitization: No specific sanitization of CLI output is shown, as the skill treats the output as status indicators.

authentication-patterns