The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected within the skill instructions. The skill focuses on repository structure, file responsibilities, and validation workflows.
[SAFE]: There are no external network requests, data exfiltration attempts, or unauthorized command executions performed by the skill. The mentioned CI tools (Bun and Turbo) are documented as recommendations for external workflows.
[SAFE]: No sensitive data access or credential exposures were identified. The instructions relate to project-specific metadata and file organization.
[SAFE]: No obfuscation, hidden content, or suspicious encoding techniques were found.
[PROMPT_INJECTION]: The skill is designed to process and validate other skill files, which is an attack surface for indirect prompt injection. However, the skill lacks the capabilities (network, shell execution, or file write) required to act on malicious instructions within that content, rendering the risk safe.

hr-skills-maintaining