jobdanmark-search

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external job postings found on Jobdanmark.dk. This represents a potential attack surface if a job listing contains malicious instructions. \n
  • Ingestion points: Job titles and descriptions are extracted from the Jobdanmark website in cli/src/commands/detail.ts. \n
  • Boundary markers: None found in the data returned to the agent. \n
  • Capability inventory: The skill utilizes Bash execution permissions to run its own CLI components. \n
  • Sanitization: Data is parsed using node-html-parser and JSON.parse for JSON-LD, but is not filtered for natural language instructions. \n- [COMMAND_EXECUTION]: The skill executes its functionality via a local CLI tool using the Bash environment, which is the standard operation mode for this skill framework.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 10:17 AM