frontend-resume
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
extract_resume.pyto parse user files and uses the systemopencommand to display the generated HTML resume in the browser. - [EXTERNAL_DOWNLOADS]: The skill relies on standard Python packages from PyPI (
pdfplumber,PyPDF2,python-docx) for parsing various document formats and references well-known external assets from Google Fonts and Fontshare. - [PROMPT_INJECTION]: The skill processes untrusted user-provided document files, which exposes a surface for indirect prompt injection.
- Ingestion points: The
scripts/extract_resume.pyutility reads content from user-provided PDF, Word, Markdown, Text, and JSON files. - Boundary markers: The skill does not use explicit delimiters or "ignore previous instructions" warnings when passing extracted resume text to the agent.
- Capability inventory: The agent has the capability to execute local scripts, perform file system write operations, and trigger the
opencommand. - Sanitization: No sanitization or filtering for malicious instructions is performed on the extracted text before it is presented to the agent.
Audit Metadata