effect-schema-brainstorming

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using @andrue/cli (e.g., andrue-cli generate) and test runners like bun:test to validate generated schemas and functional properties.
  • [DYNAMIC_EXECUTION]: The skill generates and executes TypeScript code at runtime for data sampling and testing. This includes creating one-off runners for FastCheck.sample to generate realistic domain examples and defining functional property tests in the package's test directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from existing source files, AGENTS.md documentation, and user-provided domain requirements to shape its output.
  • Ingestion points: Reads existing production schema modules, package source code, and project-specific AGENTS.md files (SKILL.md).
  • Boundary markers: None identified in the instructions to separate untrusted file content from agent instructions.
  • Capability inventory: The agent is authorized to edit production source files, create new schema modules, and execute generated test code (SKILL.md).
  • Sanitization: No specific sanitization or filtering of ingested source code or documentation is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:34 PM
Security Audit — agent-trust-hub — effect-schema-brainstorming