resume
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands for document conversion (textutil), image generation (infsh), and web deployment (wrangler deploy).
- [EXTERNAL_DOWNLOADS]: The skill fetches data from several external services, including Firecrawl for web scraping, Perplexity for industry research, and Fal AI for image processing. It also includes an external JavaScript library from cdnjs.cloudflare.com in the generated output.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from scraped URLs and user files.
- Ingestion points: Step 2 scrapes external job postings and company websites.
- Boundary markers: None are specified to separate untrusted scraped data from system instructions.
- Capability inventory: The skill has access to bash command execution and deployment tools in Step 8.
- Sanitization: There is no mention of sanitizing or escaping the content retrieved from external sources before it is used in the prompts.
- [DATA_EXFILTRATION]: The skill transmits user-provided resume data to external search engines and AI services for analysis and eventually deploys it to a public Cloudflare Workers URL.
Audit Metadata