The Agent Skills Directory

[SAFE]: The skill manages authentication securely by utilizing environment variables (LITELLM_BASE_URL and LITELLM_API_KEY) for proxy interactions, avoiding hardcoded secrets.
[SAFE]: The instructions include a mandatory confirmation step, requiring the agent to show the key alias and obtain user approval before executing destructive POST requests.
[SAFE]: Command execution is restricted to standard curl operations for API management. All actions are consistent with the skill's primary purpose and the known domain of the author, BerriAI, who develops the LiteLLM project.
[SAFE]: No evidence of prompt injection, obfuscation, privilege escalation, or unauthorized data exfiltration was found during the analysis.

delete-key