The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill makes network requests to the EachLabs API (eachsense-agent.core.eachlabs.run) to generate AI content. These operations are core to the skill's primary functionality.
[SAFE]: The skill uses placeholders like $EACHLABS_API_KEY and YOUR_EACHLABS_API_KEY for authentication, which adheres to security best practices for handling sensitive credentials.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill processes user-supplied text descriptions and image URLs (SKILL.md) as input for AI generation.
Boundary markers: The instructions do not provide explicit delimiters or instructions to ignore potential injection within the user content.
Capability inventory: The skill is designed to call external APIs using tools like Bash(curl) and WebFetch to process this data.
Sanitization: There is no explicit sanitization of inputs mentioned in the skill; safety relies on the downstream AI model's own guardrails.

tiktok-content