The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines tools that ingest external job listings and documentation, creating a potential surface for indirect prompt injection where malicious instructions could be embedded in the fetched content.
Ingestion points: Data enters the agent context through tools like search_jobs, search_upwork_jobs, and search_docs which query https://jobspipe.dev/mcp and https://docs.jobspipe.dev/mcp.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are defined for the tool outputs.
Capability inventory: The tools are described as read-only (readOnlyHint: true), limiting the immediate impact of injected instructions to context manipulation.
Sanitization: The skill instructions do not specify any sanitization, filtering, or validation processes for the ingested external data.

jobspipe-mcp