The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a shell script find-polluter.sh that executes npm test on files matching a user-provided pattern. This is a standard utility for identifying flaky or polluting tests in a development environment.
[DATA_EXFILTRATION]: Documentation in SKILL.md contains examples for inspecting system configurations using commands like security list-keychains and security find-identity -v. While these commands access system identity data, they are presented as diagnostic steps for debugging build and signing failures.
[PROMPT_INJECTION]: The skill processes external error messages and test outputs, creating an indirect prompt injection surface.
Ingestion points: SKILL.md (Stage 1: reading error messages), find-polluter.sh (scanning file outputs).
Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded within the logs being analyzed.
Capability inventory: Shell execution via npm test and suggested CLI diagnostics.
Sanitization: Not present; error messages are analyzed directly for debugging patterns.

systematic-debugging