The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs users to execute npx jobgpt-mcp-server, which downloads and runs external code from the NPM registry.
[EXTERNAL_DOWNLOADS]: The skill requires communication with a remote endpoint at https://mcp.6figr.com/mcp to perform core functions like job matching and application tracking.
[PROMPT_INJECTION]: The import_job_by_url tool enables the agent to ingest content from arbitrary external job boards, creating a surface for indirect prompt injection attacks.
Ingestion points: External job descriptions imported via URLs through the import_job_by_url tool (SKILL.md).
Boundary markers: The instructions lack delimiters or warnings to treat imported job content as untrusted data.
Capability inventory: Significant capabilities including apply_to_job, generate_resume_for_job, and send_outreach are available to process the imported data.
Sanitization: No evidence of sanitization, filtering, or validation for content fetched from remote job boards.

jobgpt