The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs the agent to run npx zai-cli, which downloads and executes a package from the public npm registry at runtime. This package is not from a verified or trusted organization.
[COMMAND_EXECUTION]: The skill relies on the Bash tool to execute the zai-cli commands for its primary functions, including vision analysis, web searching, and repository exploration.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its data processing workflows.
Ingestion points: Untrusted content is ingested from the live web (via search and reader), visual media (via vision), and external GitHub repositories.
Boundary markers: No delimiters or safety instructions are provided to help the agent distinguish between the skill's instructions and the external data being processed.
Capability inventory: The skill possesses extensive capabilities, including Bash(cmd:*), WebFetch, and file modification tools (Write, Edit), creating a high-impact surface for malicious instructions.
Sanitization: There is no evidence of validation or sanitization of the external content before it is processed by the AI.

zai-cli