github Python re-analysis due

sandraschi/deepfang

github

Execution sandbox for AI agents with three-stage sanitize, adjudicate, execute pipeline

maintainer
sandraschi
licence
MIT
first seen
2026-06-30
last seen
2026-09-06
releases · 30d
0
short id

sandraschi/deepfang is an MCP server distributed on github, maintained by sandraschi, tracked here since June 2026. It has shipped 0 releases and exposes 7 tools. Tools include deepfang_adjudicate, deepfang_agentic_workflow, deepfang_audit, deepfang_dispatch, deepfang_pipeline, deepfang_sanitize, and 1 more. Its composite risk grade is A — an inferred review prompt computed from observed signals, not a verdict.

what we found

Its 7 tools appear to reach database, inferred from tool names, descriptions and input schemas rather than from observed behaviour.

full security breakdown →
tools 7
  • deepfang_adjudicate Stage 2 only — LLM verdict with rationale
  • deepfang_agentic_workflow Multi-step goal via FastMCP 3.2 sampling
  • deepfang_audit Query the adjudication log
  • deepfang_dispatch Stage 3 only — requires prior approval in audit log
  • deepfang_pipeline Full pipeline in one call — the main entry point
  • deepfang_sanitize Stage 1 only — fast regex scan, returns threat score
  • deepfang_status Health check across all pipeline services
release cadence · 90d 0 releases

No releases yet.

recent releases last 0

No releases yet.