The Agent Skills Directory

[SAFE]: The skill facilitates interaction with the platform-native alera CLI tool using pre-defined environment variables (ALERA_WORKSPACE_ID, ALERA_TERMINAL_SESSION_ID) for session identification and scoping. No unauthorized command execution or resource access patterns were detected.- [SAFE]: The documentation includes explicit security constraints for the agent, such as the prohibition of arbitrary commands, source code, external requests, and URLs in published actions, adhering to the principle of least privilege.- [INDIRECT_PROMPT_INJECTION]: The skill utilizes alera canvas wait to receive decisions and alera canvas catalog to retrieve workspace history, which serve as ingestion points for external data. However, the risk is mitigated by explicit boundary rules and formatting requirements described in the contract, and no exploitation surface for high-severity capabilities was identified.

alera-agent-canvas