gws-slides

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gws command-line utility to interact with Google Slides API resources. The commands allow for reading, creating, and updating presentations, which is consistent with the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it retrieves data from external Google Slides presentations.
  • Ingestion points: The presentations.get and pages methods described in SKILL.md retrieve external content.
  • Boundary markers: The instructions do not specify any markers or delimiters to isolate untrusted presentation content from the agent's instructions.
  • Capability inventory: The skill has the capability to execute shell commands via the gws tool.
  • Sanitization: There is no mention of sanitizing or validating presentation content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:27 PM
Security Audit — agent-trust-hub — gws-slides