seed-deprecation

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The workflow involves running bun run rootage:generate to refresh generated files after configuration changes. This is a standard project-specific build operation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user input for deprecation reasons and targets, which are then placed into JSDoc and YAML files.
  • Ingestion points: User-provided parameters in references/guide.md (Target, Deprecated In, Remove In, Replacement, Reason).
  • Boundary markers: None identified; user input is interpolated directly into templates.
  • Capability inventory: The skill permits modification of source code, documentation, and configuration files, along with shell command execution for build scripts.
  • Sanitization: No validation or escaping of user-provided strings is mentioned before they are written to the filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 05:48 AM
Security Audit — agent-trust-hub — seed-deprecation