skill-sync

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides shell scripts (sync.sh and sync_test.sh) designed to be executed via the Bash tool to automate project documentation updates. The scripts use standard POSIX utilities (awk, sed, grep, find) to process local files.
  • [DATA_INJECTION_SURFACE]: The synchronization process reads metadata (scope and auto-invoke instructions) from other SKILL.md files in the repository and interpolates them into AGENTS.md files. While this creates a surface where one skill can influence the documentation (and thus the behavior) of an agent reading AGENTS.md, this is the intended primary purpose of the skill. The script performs basic sanitization and formatting to ensure the data is placed correctly within Markdown tables.
  • [NO_REMOTE_ASSETS]: The skill does not perform any network operations, download external dependencies, or reference remote resources, significantly reducing its attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 02:57 AM