The Agent Skills Directory

[SAFE]: No malicious patterns, such as credential harvesting, exfiltration, or unauthorized command execution, were detected.
[NO_CODE]: The skill consists entirely of descriptive natural language instructions for multimodal analysis and does not contain any scripts, executables, or automated tool configurations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external visual data (screenshots, diagrams, video frames), which serves as an ingestion point for potential indirect prompt injection. However, the skill does not implement any dangerous capabilities that could be exploited by such an injection.
Ingestion points: Visual data processing (SKILL.md)
Boundary markers: Absent
Capability inventory: No file system access, network operations, or subprocess execution defined
Sanitization: Absent

multimodal-looker