The Agent Skills Directory

[COMMAND_EXECUTION]: The skill functions by executing the ve volclog command-line utility to perform log management tasks, including project creation, topic resolution, and log searching as detailed in SKILL.md and the SOPs.
[EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of the @volcengine/cli Node.js package from the official NPM registry to provide the necessary ve binary.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to search and analyze log data, which represents an attack surface for indirect prompt injection if malicious instructions are embedded within the log content.
Ingestion points: External data enters the context through log.search, log.export, and log.ingest commands described across all reference files.
Boundary markers: The skill does not implement explicit LLM boundary markers for log content, but it strongly prefers structured JSON processing to minimize misinterpretation.
Capability inventory: The skill possesses the capability to execute shell commands, read/write files via the CLI, and perform network requests through the Volcengine API.
Sanitization: There is no explicit sanitization or filtering of log data content before it is presented to the agent.

volcengine-tls