concept-atlas-dense-explain
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the
concept-atlas-dense-explainpackage from the npm registry using thenpxutility during validation and compilation steps. - [REMOTE_CODE_EXECUTION]: Running
npx concept-atlas-dense-explainresults in the execution of code from a remote repository at runtime. - [COMMAND_EXECUTION]: The core functionality relies on executing shell commands to manage the document generation lifecycle, including creation, validation, and HTML compilation.
- [INDIRECT_PROMPT_INJECTION]: The skill converts untrusted user input (topics or existing files) into MDX-based documentation, presenting a potential vector for indirect prompt injection.
- Ingestion points: Untrusted content enters the system when users provide topics or documents to be processed (referenced in
SKILL.md). - Boundary markers: The instructions do not prescribe the use of delimiters to segregate user content from the agent's prompts.
- Capability inventory: The skill can execute shell commands, perform local file I/O, and generate standalone HTML files.
- Sanitization: There are no explicit instructions for sanitizing or escaping the user-provided data before it is formatted into MDX components.
Audit Metadata