The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Jobnet.dk job listings, including job titles, descriptions, and employer names. This content is processed by the agent and could contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Data enters the agent's context through the search and detail commands implemented in cli/src/commands/search.ts and cli/src/commands/detail.ts.
Boundary markers: The skill does not employ explicit delimiters or system instructions to warn the agent about potentially malicious content within the job data.
Capability inventory: The agent has access to the Bash tool to execute the CLI, which creates a risk if an injection successfully tricks the agent into executing arbitrary shell commands.
Sanitization: While cli/src/helpers.ts includes a stripHtml function to clean HTML tags from descriptions, this does not filter or sanitize the natural language content for injection patterns.

jobnet-search