find-vc-backed-ai-jobs-munich
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to crawl and extract data from external, third-party sources such as company careers pages, job boards, and venture capital portfolio sites.
- Ingestion points: Data is ingested through browser automation and web extraction from numerous external domains listed in
SKILL.md(e.g., LinkedIn, Y Combinator, VC portals). - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the extracted job descriptions.
- Capability inventory: The skill uses browser automation for data extraction and integrates with MCP/API tools to write findings to a Notion database or tracker.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the extracted HTML/text before it is processed by the agent to generate rationales.
Audit Metadata