The Agent Skills Directory

[Command Execution] (SAFE): The skill suggests using the fd utility to locate directories. This is a common, non-destructive file-finding tool.
[Indirect Prompt Injection] (LOW): The skill is designed to process external content (other SKILL.md files). While this presents an ingestion surface for untrusted data, the skill does not possess capabilities that would allow for exploitation, such as network exfiltration or persistent file system modifications.
[Data Exposure] (SAFE): The skill only reads metadata from within the project's own skills/ directory for validation purposes and does not access sensitive system files or credentials.

validate-skills