The Agent Skills Directory

[SAFE]: The skill utilizes the official @membranehq/cli for all interactions with Annature. This approach ensures that sensitive operations, such as authentication and API requests, are managed by the vendor's established infrastructure rather than custom, potentially unsafe scripts.
[SAFE]: No hardcoded credentials, sensitive file path access, or malicious network exfiltration patterns were detected. The instructions explicitly direct the agent to use secure connections instead of asking the user for tokens.
[SAFE]: The skill exhibits no signs of obfuscation, persistence mechanisms, or privilege escalation attempts.
[SAFE]: The skill has a standard indirect prompt injection surface as it processes external data from Annature (e.g., document content or envelope lists).
Ingestion points: Data enters the agent context through the output of membrane action run commands in SKILL.md.
Boundary markers: None explicitly defined in the provided instructions.
Capability inventory: The skill possesses network access capabilities via the membrane CLI tool.
Sanitization: No explicit sanitization of external data is described. This is a common characteristic of data-processing skills and does not pose an immediate threat.

annature