review-dependencies
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard package manager commands (e.g.,
npm,pip,cargo,go,gh) to discover dependency information. These are legitimate uses within the scope of a developer auditing tool. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project configuration files (like
package.json,pyproject.toml, and GitHub Actions workflows). While it lacks explicit boundary markers for this data, the risk is minimal as the agent uses specific tools to extract versioning data rather than interpreting the files as instructions. - Ingestion points: Project configuration files such as
package.json,Cargo.toml, and.github/workflows/*.yml. - Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: Executes shell commands for package analysis and uses
gh apifor GitHub interactions. - Sanitization: Relies on the underlying CLI tools to parse structured data (JSON/YAML/TOML).
- [EXTERNAL_DOWNLOADS]: The skill suggests the installation of well-known developer utilities like
npm-check-updatesif they are missing from the user's environment, which is standard practice for this functionality.
Audit Metadata