jd-tailorer
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill uses
npx -p @chasen-liao/resume-skills@latestto fetch and execute code from the NPM registry. While NPM is a well-known service and the package identifier corresponds to the vendor, this mechanism facilitates the execution of remote code at runtime. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external Job Descriptions (JD) which could contain malicious instructions.
- Ingestion points: Job description text, uploaded files, or职位链接 provided by the user in Step 1 of the workflow.
- Boundary markers: No explicit instructions are provided to the agent to ignore potentially malicious instructions embedded within the Job Description text.
- Capability inventory: The skill writes files to the local file system (tailored/ directory) and executes shell commands via
python,npx, and PowerShell scripts. - Sanitization: The skill lacks explicit sanitization or validation of the JD content before using it to generate the matching analysis and tailored resume content.
- [COMMAND_EXECUTION]: The skill executes several local and remote-sourced commands as part of its quality audit and rendering process:
python skills/resume-builder/scripts/validate_resume.pynpx -p @chasen-liao/resume-skills@latest resume-skills validaterender_resume.ps1npx -p @chasen-liao/resume-skills@latest resume-skills editor
Audit Metadata