preview-og
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the @hungv47/metaprev package. This is a vendor-owned resource originating from the skill author.
- [REMOTE_CODE_EXECUTION]: Playbook instructions include the standard installation method for the Bun runtime via the official script at https://bun.sh/install. This is a well-known technology service and is considered safe.
- [PROMPT_INJECTION]: The skill's diagnostic process involves reading external URLs, which represents a potential indirect prompt injection surface. This is an inherent part of the skill's primary function and is mitigated by structured output and re-verification steps.
- Ingestion points: Data from external URLs processed by the metaprev CLI.
- Boundary markers: Structured JSON output from the CLI used for agent reasoning.
- Capability inventory: Use of Bash, Write, and Edit tools to apply remediations to the codebase.
- Sanitization: The skill relies on structured tool output rather than raw web content to guide its logic.
Audit Metadata