jobbank-search

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches job listing data from https://jobbank.dk using its public RSS feed and HTML search results. This is the primary function of the tool and uses standard web protocols.
  • [COMMAND_EXECUTION]: The skill provides a CLI tool implemented in Node.js/Bun. It performs network requests and data parsing as part of its core functionality, without providing arbitrary shell execution or unsafe command interpolation.
  • [PROMPT_INJECTION]: As the skill processes external content from job postings, it is susceptible to indirect prompt injection. However, this is inherent to tools processing web content.
  • Ingestion points: RSS feed data in cli/src/commands/search.ts and HTML detail pages in cli/src/commands/detail.ts.
  • Boundary markers: Not explicitly provided in instructions to the agent.
  • Capability inventory: Data fetching and formatting output.
  • Sanitization: HTML tags are removed during plain-text output processing in cli/src/commands/detail.ts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:20 PM
Security Audit — agent-trust-hub — jobbank-search