markmap
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a shell script
scripts/render.shto executemarkmap-clivianpx. This is the primary intended function for generating offline mindmaps and uses a pinned version of the package. - [EXTERNAL_DOWNLOADS]: The
scripts/render.shscript may download themarkmap-cli@0.18.12package from the official npm registry if not already present. Additionally, theassets/template.htmlfile references officiald3andmarkmaplibraries from the well-knownjsdelivr.netCDN. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided notes and documents. It includes a specific security posture section (Section 7) that instructs the agent to stop if sensitive information like credentials or PII is detected in the input. It also implements sanitization by encoding Markdown as JSON and escaping
<characters to prevent XSS during HTML generation. - [OBFUSCATION]: No obfuscation or hidden logic was detected in the provided files.
- [PRIVILEGE_ESCALATION]: The skill does not request or attempt to gain elevated privileges; it operates within the standard user environment.
Audit Metadata