adaptogen-run

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill requires the agent to paste "anything it needs" into the dispatched prompt and to report literal command output and file edits, which can force inclusion and verbatim output of secrets (API keys, tokens, passwords) if they are needed or appear in outputs.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill explicitly requires dispatched agents (or the leaf-agent) to "actually run" the target's procedures and "report literal edits made" and to call whatever tools the target's text says to call, which encourages executing commands and making file edits that can change machine state even if it does not specifically request sudo or specific system-file changes.