updating-npm-package
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard npm and npx commands to manage packages, including
npm install,npm test,npm run build, andnpx @next/codemod. These are necessary for the skill's primary purpose of updating dependencies. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data which could theoretically contain malicious instructions.
- Ingestion points: Reads package metadata via
npm view, retrieves content from remoteCHANGELOG.mdorMIGRATION.mdfiles, and processes web search results for migration guides. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' warnings when the agent reads this external content.
- Capability inventory: The skill maintains capabilities to install packages and execute arbitrary shell commands via npm scripts.
- Sanitization: There is no explicit validation or filtering of the text retrieved from remote documentation sources before the agent acts upon it.
Audit Metadata