upgrade-deps
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard, non-interactive package management commands such as
bun install,bun update, andbun audit. These operations are central to the skill's purpose and follow best practices for automated dependency management without introducing excessive privileges. - [INDIRECT_PROMPT_INJECTION]: The skill instructions identify the risk of malicious instructions in external documentation. 1. Ingestion points:
references/major-upgrades.md. 2. Boundary markers: Present (explicit instruction to ignore commands in text). 3. Capability inventory:bun install,bun update,git. 4. Sanitization: Manual user review required. - [REMOTE_CODE_EXECUTION]: The skill supports running official codemods via
bunx. It mitigates risk by advising the use of only reviewed, official tools and warning against community-provided scripts.
Audit Metadata