The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a shell script, find-polluter.sh, which runs npm test on files to detect test environment pollution. It also provides examples for diagnostic commands such as security list-keychains and codesign to troubleshoot system-level issues.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external error logs and stack traces, which are untrusted data sources. 1. Ingestion points: The agent is instructed to read error messages and gather evidence in systematic-debugging/SKILL.md. 2. Boundary markers: No specific delimiters or instructions to ignore embedded commands in logs are provided. 3. Capability inventory: The skill allows the agent to execute shell commands and write to the filesystem to fix bugs or add logging. 4. Sanitization: The skill does not describe any method for sanitizing or escaping the log data it processes.

debugging