ae-workspace
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the vendor-specific
ae-clitool to perform various AgentSpace operations, including workspace creation, deletion, and file management. - [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data sources that could be used to host malicious instructions intended to influence the agent's behavior.
- Ingestion points: The agent can read content from workspace assets (
asset read) and inspect workspace activity logs (activity list) as detailed inreferences/commands.md. - Boundary markers: The instructions do not specify the use of clear delimiters or warnings for the agent to ignore instructions embedded within the retrieved file content or activity data.
- Capability inventory: The skill possesses significant write capabilities via
ae-cli, including the ability to delete workspaces, modify member roles, and reconfigure workspace capabilities (capability set). - Sanitization: There is no mention of sanitizing, escaping, or validating the data retrieved from external assets or logs before it is processed by the agent.
Audit Metadata