cleanup-types

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell commands for static analysis and build verification.
  • It executes grep to scan source files for type definitions across TypeScript, Python, Go, and Rust.
  • It runs compiler and testing tools including tsc, mypy, go, cargo, and bun to verify that proposed code changes do not introduce regressions.
  • [PROMPT_INJECTION]: The skill processes untrusted local source code, which constitutes an indirect prompt injection surface.
  • Ingestion points: The skill ingests raw code content from local workspace files (.ts, .py, .go, .rs) using the grep utility (SKILL.md).
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded content when processing the results of the code scan.
  • Capability inventory: The skill has permissions to write to the file system (modifying source code and writing reports) and execute various CLI tools in the shell (SKILL.md).
  • Sanitization: The skill does not perform specific sanitization or escaping of the content found within type definitions before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 06:16 AM
Security Audit — agent-trust-hub — cleanup-types