The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local system commands such as git log and kubectl to gather activity history. It also uses a vendor-specific tool, joelclaw, to query system runs and telemetry stats. These operations are consistent with the skill's stated purpose of generating a system report.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, including git commit messages and system logs, which may contain untrusted content. 1. Ingestion points: The skill reads output from git log in local directories and telemetry data from joelclaw otel search commands. 2. Boundary markers: There are no explicit instructions to the agent on how to handle or ignore potentially malicious instructions embedded within these logs. 3. Capability inventory: The skill possesses the ability to read local file histories and execute system monitoring commands. 4. Sanitization: No sanitization or filtering of the ingested content is described in the instructions.

daily-summary