gws-slides
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides functionality to read presentation data via
gws slides presentations get. This content is untrusted data that could contain malicious instructions intended to manipulate the agent's subsequent actions. - Ingestion points: Presentation content retrieved through the
getmethod. - Boundary markers: None explicitly defined in this file to separate data from instructions.
- Capability inventory: The skill can modify presentations (
batchUpdate), create new ones (create), and execute shell commands through thegwsbinary. - Sanitization: No explicit sanitization of presentation content is described within this skill file.
- [COMMAND_EXECUTION]: The skill relies on executing the
gwsCLI tool to perform its primary functions. This is consistent with the intended purpose of providing a Google Slides interface.
Audit Metadata