The open detection-signature library for AI-agent threats — prompt injection, jailbreaks, tool poisoning. Mapped to MITRE ATLAS + OWASP LLM Top 10. nuclei-templates for AI agents.
Drift inferred · capture-to-capture
No drift recorded — single capability capture; advisories appear once its surface changes.
transport stdio counts 0 tools · 0 res
· 0 prompts
permission surface via code analysis
No tools enumerated yet for this server.
evidence-backed
findings quoted directly from the published source artifact — not inferred
code files: 4
filesystem 1
- fs cognis-digital-agentsigs-f12e026/agentsigs/engine.py :54
doc = json.load(open(os.path.join(d, fn), encoding="utf-8"))
declared dependencies 1
- pytest@>=8.0