gws-slides

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gws binary to perform API actions and requires the agent to dynamically construct command flags based on schemas found at runtime.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface. 1. Ingestion points: Untrusted data enters via the presentations.get method (SKILL.md). 2. Boundary markers: The skill lacks specific delimiters or guidelines to ignore embedded instructions in slides. 3. Capability inventory: The agent has shell access to execute gws commands for creating and updating content. 4. Sanitization: No sanitization or validation of retrieved content is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:56 PM