The Agent Skills Directory

[COMMAND_EXECUTION] (LOW): The skill includes find-polluter.sh, a shell script that executes npm test on files matching a provided pattern. This is a legitimate debugging utility but represents a command execution capability.
[COMMAND_EXECUTION] (LOW): SKILL.md provides examples for running diagnostic shell commands such as security list-keychains and codesign to debug build and signing issues. These are instructional and typical for technical debugging.
[PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) due to its core function of analyzing untrusted external data.
Ingestion points: Error messages, stack traces, and git diffs are ingested for analysis in SKILL.md (Phase 1) and root-cause-tracing.md.
Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the log data being analyzed.
Capability inventory: The skill possesses the ability to execute shell commands (npm test, security, codesign).
Sanitization: Absent; the skill does not mandate sanitization or escaping of the ingested data before processing.

systematic-debugging