gws-docs-write

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the gws command-line tool, which is a recognized vendor resource for the googleworkspace author.
  • [INDIRECT_PROMPT_INJECTION]: The skill is a sink for external data that could potentially contain malicious instructions or shell metacharacters.
  • Ingestion points: The --document and --text flags accept arbitrary strings.
  • Boundary markers: None identified.
  • Capability inventory: The skill facilitates document modification via a shell-based CLI.
  • Sanitization: Input validation or escaping is not defined in the skill logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:58 AM
Security Audit — agent-trust-hub — gws-docs-write