js-skills
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to retrieve a remote documentation file from
https://raw.githubusercontent.com/mj-studio-library/js-util/master/llms.txtto guide its refactoring and code implementation logic. - [COMMAND_EXECUTION]: The instructions permit the agent to install the
@mj-studio/js-utilpackage via npm or yarn if requested by the user and not already present. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on external, unvalidated instructional content.
- Ingestion points: The agent is directed to fetch and obey instructions from an external URL in
rules/js-util-usage.md. - Boundary markers: No delimiters or isolation instructions are provided to the agent to differentiate the external content from its core instructions.
- Capability inventory: The agent has the capability to modify project code and install software packages based on information retrieved from the external source.
- Sanitization: There is no mechanism described for validating or sanitizing the content fetched from the remote repository.
Audit Metadata