resume-cv-builder
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard shell utilities (
tr,grep,sort,uniq,head) and thepandocbinary to process text and convert documents. These tools are appropriate for the skill's stated purpose of resume building and keyword optimization. - [EXTERNAL_DOWNLOADS]: References a CSS stylesheet from the jsDelivr CDN (
water.css) for styling generated HTML resumes. This is a reference to a well-known service used for legitimate content delivery. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content (resumes) and external job descriptions.
- Ingestion points: Job descriptions and user-supplied professional history (SKILL.md).
- Boundary markers: The instructions use placeholders like
[paste JD]to delimit external content. - Capability inventory: Shell pipes for text processing and
pandocfor file generation. - Sanitization: None explicitly defined, but the operations are limited to text frequency counting and document formatting.
- [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected. The skill functions as a legitimate productivity tool for career documentation.
Audit Metadata