schema-updater

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted artifacts, creating a surface for indirect prompt injection attacks.
  • Ingestion points: Step 0 involves reading schema files and associated artifacts (skills, agents, hooks) using Read, Glob, and Grep tools.
  • Boundary markers: The skill does not define clear boundaries or provide instructions for the agent to ignore instructions embedded in the processed artifacts.
  • Capability inventory: The agent is empowered with Write, Edit, and Bash tools, which could be misused if influenced by malicious content in an artifact.
  • Sanitization: There is no requirement for sanitization or validation of artifact content before processing.
  • [COMMAND_EXECUTION]: The skill workflow includes the execution of shell commands using the Bash tool.
  • Evidence: Step 4 directs the agent to run 'pnpm lint:fix && pnpm format', which executes scripts defined in the project's configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 01:52 AM
Security Audit — agent-trust-hub — schema-updater