google-spaces-updates

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git to collect project context and curl to send notifications to Google Chat, which are standard operations for its purpose.
  • [DATA_EXFILTRATION]: The skill reads git history and transmits it to a user-defined Google Chat webhook. This is the core feature of the tool and utilizes a well-known service.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface by processing git log and diff data. Ingestion points include git commit messages and diffs. Boundary markers consist of markdown templates without explicit isolation of untrusted data. Capability inventory includes network access and file writing. Sanitization is addressed by instructions to escape quotes in generated shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:49 AM