The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze job logs and execution details from external sources using tools like webdav_get and logs_get_recent. These logs are considered untrusted data that could potentially contain malicious content or instructions aimed at influencing the agent's logic.
Ingestion points: Job log files retrieved via webdav_get (SKILL.md, Step 3) and parsed log entries via logs_get_recent (references/job-logs.md).
Boundary markers: The instructions do not specify the use of delimiters or warnings to separate log content from the agent's instructions.
Capability inventory: The skill environment includes file read capabilities (webdav_get, webdav_list) and CLI execution via the b2c toolset.
Sanitization: No explicit validation or sanitization steps are documented for the log data before it is processed by the agent.
[COMMAND_EXECUTION]: The skill relies on the b2c CLI tool for several operations including b2c setup inspect, b2c job search, and b2c job log. These are standard administrative commands required for the skill's primary function of job health monitoring.

b2c-job-health