The Agent Skills Directory

[SAFE]: The skill provides standard documentation for interacting with a video generation service and does not include any malicious scripts, persistence mechanisms, or privilege escalation attempts.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text through the 'prompt' parameter in the curl examples (SKILL.md). While there are no explicit boundary markers or sanitization routines mentioned in the examples, this ingestion is the primary purpose of the skill. The only available capability is a network request to the service provider.
[DATA_EXFILTRATION]: The skill uses curl to transmit data to the vendor's official API endpoint (api.eachlabs.ai). This is a documented functional requirement for the skill's operation.
[SAFE]: API credentials are managed securely through the use of environment variables ($EACHLABS_API_KEY) rather than being hardcoded in the skill text.

veo-3