skills/kcchien/skills/gws-docs/Gen Agent Trust Hub

gws-docs

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill provides the capability to fetch content from Google Documents, which introduces a surface for indirect prompt injection where malicious instructions in a document could influence agent behavior. * Ingestion points: The gws docs documents get command described in SKILL.md imports data into the agent's active context. * Boundary markers: Absent. No specific delimiters or instructions are provided to help the agent isolate external data from its core instructions. * Capability inventory: The skill has the ability to read (get), create (create), and modify (batchUpdate) documents via the gws CLI. * Sanitization: Absent. There is no evidence of validation or filtering of the content retrieved from documents.
  • [COMMAND_EXECUTION]: The skill invokes the gws binary to execute operations against the Google Docs API as specified in the usage documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 03:09 PM
Security Audit — agent-trust-hub — gws-docs