ai-dev-jobs-mcp

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes job descriptions and requirements fetched from an external repository (aidevboard.com). This content is authored by third-party job posters and could potentially contain instructions aimed at influencing the agent's behavior during analysis or matching tasks.
  • Ingestion points: External data is ingested in SKILL.md via tools like search_jobs and get_job which retrieve remote content from https://aidevboard.com/mcp.
  • Boundary markers: The instructions lack explicit boundary markers or 'ignore embedded instructions' warnings for the data retrieved via the MCP server.
  • Capability inventory: The skill allows the agent to match candidate profiles to jobs and summarize listings, though it does not explicitly grant file-write or subprocess execution within the provided file.
  • Sanitization: There is no evidence of output sanitization or filtering for the data returned by the remote tools.
  • [EXTERNAL_DOWNLOADS]: The skill requires configuration of a remote MCP server endpoint at https://aidevboard.com/mcp. This is a vendor-provided resource for the AI Dev Jobs board, used to bridge the agent to the live job index.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 12:58 PM