The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety guidelines were detected in the instructions or metadata.
[DATA_EXFILTRATION]: The skill operates on SQL-level cluster settings. While it provides procedures for managing enterprise licenses (e.g., enterprise.license), it does so through standard database administrative commands without any unauthorized network operations or exfiltration patterns.
[REMOTE_CODE_EXECUTION]: No remote script downloads or execution patterns (e.g., curl | bash) were identified. The skill relies entirely on standard SQL commands and CLI flags.
[COMMAND_EXECUTION]: The skill includes shell commands for starting CockroachDB nodes with specific flags (e.g., cockroach start). These are documented procedures for cluster management and do not involve arbitrary command execution or shell injection vulnerabilities.
[CREDENTIALS_UNSAFE]: No hardcoded secrets or credentials were found. The skill uses appropriate placeholders like <license-key> for sensitive inputs.
[OBFUSCATION]: No obfuscated content, encoded strings, zero-width characters, or hidden URLs were detected during analysis. All instructions and SQL queries are in plain text.
[EXTERNAL_DOWNLOADS]: All external links point to the official CockroachDB documentation (cockroachlabs.com), which is a well-known and trusted source for this vendor's skill.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not use any dynamic context injection patterns (e.g., !command syntax) to execute shell commands at load time.

managing-cluster-settings