The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected within the skill's instructions or reference files. The skill correctly identifies and warns against dangerous practices like hardcoded secrets and raw SQL string concatenation.
[INDIRECT_PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection as it reads and processes external source code using the Read, Glob, and Grep tools. However, the risk is minimized as the skill is restricted to read-only operations and lacks capabilities for code execution, file modification, or network exfiltration.

security-checklist