The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions to override agent behavior or bypass safety filters were detected. The skill is strictly instructional and procedural.- [Data Exposure & Exfiltration] (SAFE): No access to sensitive file paths or network operations was found. The credential examples (e.g., 'sk-abc123...') are documented as vulnerabilities to avoid and are not functional secrets.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not include external package files or remote script execution patterns. It relies solely on built-in read-only tools.- [Indirect Prompt Injection] (SAFE): While the skill is designed to process untrusted external code, which constitutes a vulnerability surface, the restricted capability set (Read, Glob, Grep) prevents any ingested instructions from performing unauthorized actions.- [Dynamic Execution] (SAFE): No patterns of runtime code generation or dynamic loading were identified.

security-review