The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains reference files and regex patterns in references/prompt-injection-patterns.md and scripts/scan_skill.py that describe various injection techniques. These are documented for the purpose of identification and security auditing and do not represent instructions to the agent itself.
[COMMAND_EXECUTION]: The skill uses the Bash tool to run its bundled static analysis script (scan_skill.py). This is a justified use of the tool for its core functionality.
[EXTERNAL_DOWNLOADS]: The skill's bundled script requires the pyyaml package, which is a standard and well-known utility for processing YAML data.
[DATA_EXFILTRATION]: The workflow involves reading files from the local filesystem for analysis. No network exfiltration or unauthorized data access was detected.

skill-scanner