you-dont-need-isr
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configures GitHub Actions workflows to use official actions from the
actionsorganization and installs thevercelCLI from the NPM registry. - [COMMAND_EXECUTION]: Utilizes the GitHub CLI (
gh) to list workflow runs and recommends the Vercel CLI for building and deploying project artifacts. - [DATA_EXFILTRATION]: Performs network operations via
WebFetchto retrieve pricing and resource specifications fromubicloud.comandvercel.com. These are well-known technology and cloud service providers relevant to the skill's purpose. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes untrusted data from local project files and external web content to generate code suggestions.
- Ingestion points: Local Next.js source code (App and Pages routers), project configuration files (
package.json,next.config), and data retrieved from external pricing pages. - Boundary markers: No specific delimiters or safety instructions are used to separate external data from the analysis logic.
- Capability inventory: File system access, network operations (
WebFetch), command execution via CLI tools, and draft pull request generation. - Sanitization: No explicit content sanitization or validation of the ingested code or web content is performed.
Audit Metadata