jobindex-search

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves job listing information and full descriptions from the official Danish job portal at https://www.jobindex.dk. These requests are necessary for the skill's primary function and target a well-known service.
  • [COMMAND_EXECUTION]: The agent is authorized to execute the skill's CLI tool using bun run. This command execution is limited to the scripts provided within the skill package.
  • [PROMPT_INJECTION]: The skill processes content from third-party job listings, which constitutes an indirect prompt injection surface.
  • Ingestion points: Job listing data is fetched from the Jobindex.dk website in the search and detail commands located in cli/src/commands/.
  • Boundary markers: The CLI outputs data in structured JSON, table, or plain-text formats, providing a clear structure for the agent.
  • Capability inventory: The agent can execute the local CLI via Bash, which in turn has network access to retrieve web content.
  • Sanitization: The CLI implements regex-based HTML tag stripping and entity decoding in cli/src/helpers.ts and cli/src/commands/detail.ts to convert HTML content into plain text before presenting it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 10:10 AM