gws-chat-send
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gwsbinary to perform write operations in Google Chat spaces. - [INDIRECT_PROMPT_INJECTION]: The skill takes arbitrary string input via the
--textparameter and transmits it to an external messaging platform. This creates a potential surface for indirect prompt injection if the agent uses untrusted data (e.g., from a web search or email) to populate the message body. - Ingestion points: The
--textargument within the usage example inSKILL.md. - Boundary markers: No boundary markers or instructions to ignore embedded commands are present in the command template.
- Capability inventory: Subprocess execution of the
gwsCLI tool (as defined inSKILL.md). - Sanitization: No sanitization or input validation logic is specified to prevent malicious payloads in the message text.
Audit Metadata