sync-public-skills

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill manages repository state by executing local PowerShell scripts (Sync-AndPush.ps1, Commit-DirtySkills.ps1, Sync-InternalSkills.ps1) and command-line interfaces including git and gh.
  • [DATA_EXFILTRATION]: Performs synchronization of local repository content to public and internal GitHub repositories via git push. This core functionality involves reading local directory structures and transmitting data to remote servers.
  • [PROMPT_INJECTION]: The skill's workflow involves auditing and classifying 'dirty' or uncommitted skill files from the local filesystem. This process creates an indirect prompt injection surface where malicious instructions within a processed file could attempt to influence the agent's classification logic or sync operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 03:51 PM
Security Audit — agent-trust-hub — sync-public-skills