The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from untrusted external sources such as job board URLs and external job listings.\n
Ingestion points: Data enters the agent context through tools like import_job_by_url (SKILL.md), search_jobs (SKILL.md), and match_jobs (SKILL.md).\n
Boundary markers: The skill instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious commands embedded within the fetched job data.\n
Capability inventory: The agent has access to several sensitive tools that could be abused if an injection is successful, including apply_to_job, send_outreach, update_profile, and upload_resume (SKILL.md).\n
Sanitization: There is no evidence of content sanitization or validation performed on the external data before it is processed by the agent.\n- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the jobgpt-mcp-server package via npm and connects to a remote MCP endpoint at https://mcp.6figr.com/mcp. These resources are provided by the official service vendor (6figr.com).

jobgpt