job-scraper
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection risk identified in the job scraping workflow.
- Ingestion points: Job posting content is retrieved from external websites (jobindex.dk, linkedin.com, etc.) via the
WebFetchtool inSKILL.md(Step 2). - Boundary markers: Absent. The skill instructions do not require the agent to use delimiters or ignore instructions embedded within the fetched HTML/text.
- Capability inventory: The skill has access to local file operations (
Read,Write,Edit) and can invoke other skills using theAgenttool (Step 5). - Sanitization: Absent. The agent extracts information (title, company, requirements) directly from the fetched page without sanitizing the input data.\n- [SAFE]: Fetches job listings from well-known job boards and professional networking sites, such as LinkedIn and Jobindex.dk.
Audit Metadata