The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a regression test script, scripts/test_profile_contract.py, which uses subprocess.run to execute the skill's own initialization and profile management scripts. These executions are scoped to the local environment and utilize sys.executable to ensure they run within the same Python context, representing standard development testing practices.
[PROMPT_INJECTION]: The references/cloud-split.md file describes an architectural pattern for protecting intellectual property by returning symbolic data tokens instead of descriptive narration to the user. While this involves concealing internal computation logic from user-visible logs, it is presented as a legitimate data protection mechanism for commercial skills and does not instruct the agent to disregard safety guidelines or override its primary directives.
[SAFE]: The skill incorporates several proactive security measures. The scripts/profile_store.py script includes a blacklist for sensitive keywords such as 'token', 'secret', and 'api_key' to prevent accidental storage of credentials in user profiles. Furthermore, scripts/validate_skill.py acts as a security linter, scanning for private absolute user paths and incomplete templates before a skill can be installed.

lov-skill-creator