The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access attempts were detected during the analysis of the skill files.
[COMMAND_EXECUTION]: The skill instructs the agent to execute a platform-provided binary (referenced via the $OD_BIN environment variable) to generate images. This is a functional requirement for the skill's purpose and uses standard command-line argument patterns.
[PROMPT_INJECTION]: The skill ingests user input (image briefs) to synthesize prompts that are subsequently passed to a shell command. While this represents a potential surface for indirect prompt injection (Category 8), the risk is minimal as the agent is responsible for the prompt construction, and the execution environment is expected to handle argument escaping.

image-poster