dependency-upgrade
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for executing package management commands (
npm,yarn,npx) and shell scripts to perform audits, install updates, and run migration tools. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it directs the agent to ingest and analyze external documentation (
CHANGELOG.md,MIGRATION.md) to create upgrade strategies. Malicious content in these files could attempt to influence the agent's actions. - Ingestion points: Processes local and remote markdown files containing changelogs and migration guides.
- Boundary markers: None; the agent is instructed to read the files directly without specified delimiters or ignore-instructions warnings.
- Capability inventory: Includes high-privilege capabilities such as package installation (
npm install), code execution vianpx, and file system write operations. - Sanitization: No validation or sanitization of the content from the processed documentation files is implemented.
- [EXTERNAL_DOWNLOADS]: Fetches a changelog file from Facebook's official GitHub repository to assist in identifying breaking changes. This is a reference to a well-known and trusted source.
Audit Metadata