The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external job postings, which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: External job descriptions are fetched and parsed from jobdanmark.dk via the detail command in cli/src/commands/detail.ts.
Boundary markers: The CLI output provides structured data in JSON, table, or plain text formats, but lacks explicit boundary markers to encapsulate external content for the agent.
Capability inventory: The skill allows the agent to search for jobs, fetch specific details, and resolve locations or categories using the provided CLI tool.
Sanitization: The tool performs basic HTML stripping and text cleaning in cli/src/helpers.ts and cli/src/commands/detail.ts, but does not filter or sanitize for natural language instructions embedded within job descriptions.

jobdanmark-search