The Agent Skills Directory

[SAFE]: The skill provides instructions for a senior design engineer persona to perform code reviews. There are no patterns of prompt injection or attempts to bypass safety guidelines.
[SAFE]: No sensitive data access or exfiltration patterns were identified. The skill does not hardcode credentials or make network requests to untrusted domains.
[SAFE]: The skill does not download or execute remote code, nor does it install any third-party packages.
[SAFE]: There are no obfuscation techniques used to hide malicious intent or URLs.
[SAFE]: The skill has an attack surface for indirect prompt injection because it processes external code diffs, but it lacks the capabilities (such as file writing or command execution) to be exploited.
Ingestion points: Processes code diffs and animation implementations provided in the user prompt.
Boundary markers: None explicitly defined in the prompt template.
Capability inventory: No subprocess calls, network operations, or file system write access detected.
Sanitization: Not applicable as the skill only outputs textual review findings.

review-animations