skills/linct96/ai/tsdown/Gen Agent Trust Hub

tsdown

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The documentation identifies several features for command execution, such as the --on-success CLI flag for post-build automation and lifecycle hooks like build:prepare and build:done that allow for the execution of arbitrary shell commands and Node.js logic.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present (Category 8). The tool ingests potentially untrusted data from source files and configuration scripts (e.g., tsdown.config.ts). It has high-privilege capabilities including file system modification and subprocess spawning. No explicit boundary markers or input sanitization mechanisms are described for these data ingestion points.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for downloading and installing various development dependencies and plugins from the public npm registry, including publint, vue-tsc, and rolldown-plugin-wasm.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 01:53 AM