npm-deps-cleanup
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the project's detected package manager (npm, pnpm, Yarn, or Bun). These commands are used to install, uninstall, explain, and deduplicate dependencies, which is the primary purpose of the cleanup tool.
- [EXTERNAL_DOWNLOADS]: The skill recommends using one-off execution commands (npx, pnpm dlx, yarn dlx, or bunx) to run analysis tools such as
knip,depcheck,syncpack, and@e18e/cli. It also refers the agent to documentation athttps://e18e.dev/docs/replacements/for dependency replacement recommendations. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes external project files which could theoretically contain malicious instructions.
- Ingestion points: The agent reads the root
package.jsonand lockfiles (e.g.,package-lock.json,yarn.lock) to determine the package manager and dependency list. - Boundary markers: No explicit boundary delimiters are used when processing the manifest or lockfile content.
- Capability inventory: The skill has the capability to execute shell commands via package managers (install, remove, dlx) and perform file system reads/writes to manifests.
- Sanitization: The skill relies on safety rules such as working in small batches and manual verification of imports/configs, but does not specify automated sanitization of the input data.
Audit Metadata