The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a standalone shell script, find-polluter.sh, that uses the find command to identify files and executes them using npm test. Furthermore, SKILL.md provides examples for running system commands such as security list-keychains and codesign to debug keychain access and certificate issues in development environments.
[INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze external, potentially untrusted data from error messages, stack traces, and build logs. 1. Ingestion points: External error logs, stack traces, and system outputs processed in Phase 1 of the debugging cycle. 2. Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the logs. 3. Capability inventory: The agent has the capability to execute shell commands via the included find-polluter.sh script and the diagnostic examples provided. 4. Sanitization: There are no procedures defined for sanitizing or validating log content before it is processed by the agent.

systematic-debugging