openwork-desktop-sync

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses bun run desktop-openwork-sync and various Git commands (git apply, git rev-parse, git status) to perform path migration and commit synchronization. These are standard operations for a development synchronization tool.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection due to its interaction with external repository data.
  • Ingestion points: The skill ingests commit messages, trailers, and file hunks from the repository located at the user-provided OPENWORK_DIR path.
  • Boundary markers: There are no visible boundary markers or instructions provided to the agent to ignore potentially malicious instructions embedded in the synced repository data.
  • Capability inventory: The skill possesses the capability to execute shell commands and modify local repository files.
  • Sanitization: No sanitization or verification mechanisms are described to filter instructions out of the ingested commit data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 08:38 AM
Security Audit — agent-trust-hub — openwork-desktop-sync