The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses node to execute local scripts for credential configuration (configure-echotik-auth.mjs) and API interaction (echotik-api.mjs).
[COMMAND_EXECUTION]: The configure-echotik-auth.mjs script modifies the user's shell configuration files (such as .bashrc or .zshrc) to persist the ECHOTIK_USERNAME and ECHOTIK_PASSWORD environment variables across sessions. While transparently documented, this constitutes a persistence mechanism that modifies global system configuration.
[EXTERNAL_DOWNLOADS]: The skill fetches a documentation index from https://opendocs.echotik.live/llms.txt to dynamically guide its behavior and parameter mapping for API calls.
[EXTERNAL_DOWNLOADS]: The skill directs the agent to interact with external image conversion endpoints and hosts (e.g., echosell-images.tos-ap-southeast-1.volces.com) to retrieve assets not directly accessible from the source.
[PROMPT_INJECTION]: The skill processes untrusted data from TikTok (comments, video captions, product descriptions) retrieved via the EchoTik API, creating a surface for indirect prompt injection.
Ingestion points: API responses processed by echotik-api.mjs containing creator profiles, video details, comments, and captions.
Boundary markers: Absent; there are no instructions to wrap or delimit external data to prevent it from being interpreted as instructions.
Capability inventory: The agent can perform network operations via echotik-api.mjs and modify system configuration files via configure-echotik-auth.mjs.
Sanitization: Absent; the instructions do not specify any validation or filtering of content retrieved from the API before it is processed by the model.

echotik-api-assistant