The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network requests to the vendor's API endpoint (eachsense-agent.core.eachlabs.run) to process logo generation tasks. These operations are essential to the skill's core functionality and target the author's own infrastructure.
[CREDENTIALS_UNSAFE]: The skill correctly uses an environment variable ($EACHLABS_API_KEY) for authentication in its code examples, which is a recommended security practice for managing secrets.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided descriptions to generate media, which introduces a surface for indirect instructions.
Ingestion points: User-provided text strings are passed into the messages field of the API request payload in SKILL.md examples.
Boundary markers: No explicit delimiters or boundary instructions are included in the provided prompt examples.
Capability inventory: The skill uses curl to communicate with the eachlabs.run domain.
Sanitization: The documentation references a 'Content policy violation' error, indicating that sanitization and safety filtering are handled by the server-side API.

logo-generation