migrate-to-rslib

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection (Category 8) because it analyzes untrusted project data to determine migration steps.
  • Ingestion points: Processes local files including package.json, tsconfig.json, and tsup.config.* (defined in SKILL.md).
  • Boundary markers: No delimiters or protective instructions are provided to prevent the agent from following malicious instructions potentially embedded in the source configuration files.
  • Capability inventory: The agent is tasked with modifying project files and executing shell commands (build scripts).
  • Sanitization: There is no explicit validation or sanitization of the content extracted from the source tool configurations.
  • [COMMAND_EXECUTION]: The workflow includes a verification step that requires executing build commands (e.g., 'Run build command to verify the project builds successfully' in SKILL.md) which could trigger arbitrary code if a project is maliciously configured.
  • [EXTERNAL_DOWNLOADS]: The checklist files reference official migration documentation hosted on rslib.rs (e.g., https://rslib.rs/guide/migration/tsc).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 07:52 AM