The Agent Skills Directory

[PROMPT_INJECTION]: The skill includes extensive documentation of prompt injection and jailbreak patterns in the file references/prompt-injection-patterns.md. These are provided for identification and analysis purposes only and do not constitute an attempt to subvert the agent's behavior.- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run its bundled static analysis script (scripts/scan_skill.py) via the uv tool. This execution is scoped to the skill's own directory and is necessary for its auditing functionality.- [EXTERNAL_DOWNLOADS]: The skill references official documentation for the uv package manager (astral.sh) and identifies well-known domains, including the author's official sentry.io domains, as trusted sources for its internal scanner.- [REMOTE_CODE_EXECUTION]: While the skill contains examples of remote code execution in its reference files to assist in auditing, it does not perform any unauthorized remote execution or download unverified code at runtime.

skill-scanner