anygen-deep-research
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
@anygen/cliNode.js package from the official registry. It also facilitates the installation of additional skills via theanygen skill installcommand, which are resources provided by the vendor. - [COMMAND_EXECUTION]: The skill executes the
anygencommand-line tool to manage authentication and perform research tasks server-side. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided topics for research, which constitutes a potential injection surface for instructions hidden in data.
- Ingestion points: User research queries, industry analysis topics, and trend requests provided in SKILL.md.
- Boundary markers: Absent; user input is interpolated directly into the research workflow.
- Capability inventory: The
anygenCLI likely performs network requests towww.anygen.ioand writes research reports to the local file system. - Sanitization: No explicit sanitization or filtering of user-supplied research parameters is described in the provided instructions.
Audit Metadata