latest-version
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The script
scripts/latest.jsfetches data from well-known official package registries including NPM, PyPI, Go Proxy, Cargo, and RubyGems, as well as documentation from GitHub and Google. These are trusted sources for package metadata and documentation. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources such as package metadata, repository descriptions, and GitHub README files.
- Ingestion points:
scripts/latest.jsfetches package descriptions and README content via the GitHub and registry APIs. - Boundary markers: No explicit boundary markers or delimiters are used in the script's output to separate external content from internal instructions.
- Capability inventory: The agent is granted the capability to write version information to project configuration files (e.g.,
package.json,go.mod). - Sanitization: While the script does not sanitize the fetched text, the skill instructions include a 'Warning Action Rule' that mandates halting execution and reporting to the user if a package is flagged, which serves as a human-in-the-loop safety measure.
Audit Metadata