google-slides
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of the
@useclawlink/clipackage vianpxto perform all Slide operations. - Evidence: Multiple instances of
npx @useclawlink/cli [command]are used for login, connection, and action execution. - [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external Google Slides presentations, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: The
googleslides_presentations_getandgoogleslides_presentations_pages_getactions retrieve external content into the agent's context. - Boundary markers: None explicitly mentioned in the instruction set to delimit untrusted slide content.
- Capability inventory: The skill has the capability to write to the filesystem (storing credentials) and execute shell commands via the CLI tool.
- Sanitization: There is no evidence of sanitization or filtering for the retrieved slide data within the provided instructions.
Audit Metadata