skills/xyaz1313/xyskill/xy-sync/Gen Agent Trust Hub

xy-sync

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches a remote UPDATE.json file via curl and interpolates the notice field directly into the agent's output. An attacker who controls the update server could provide a malicious notice containing instructions to manipulate the agent's behavior.
  • Ingestion point: scripts/xy-sync.sh (cmd_check_remote function)
  • Boundary markers: None present for the notice text.
  • Capability inventory: The skill has extensive command execution capabilities (bash scripts, git, python).
  • Sanitization: None. The raw notice string is echoed.
  • [COMMAND_EXECUTION]: The skill's primary function involves executing multiple shell scripts and git commands to synchronize files and manage repositories.
  • [EXTERNAL_DOWNLOADS]: The check-remote command performs network requests to an external URL (defined in configuration or environment variables) to check for updates.
  • [DYNAMIC_EXECUTION]: The skill executes a local Python script (tools/build_atoms.py) and uses inline Python snippets for JSON processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:59 AM
Security Audit — agent-trust-hub — xy-sync