MCP Observatory
1m ago Tracked 55,290 Last 1m ago 24h 3,023

Capability drift in PrismorSec/prismor

github PrismorSec/prismor D

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

maintainer
PrismorSec
tools
0
CVEs
0
releases
96
advisory #891733
HIGH PrismorSec/prismor

code analysis flagged committed secret in PrismorSec/prismor

current permission surface (inferred):

drift timeline for PrismorSec/prismor → security tab →

drift history for this server newest 8
  1. HIGH code analysis flagged committed secret in PrismorSec/prismor
  2. HIGH code analysis flagged committed secret in PrismorSec/prismor
  3. HIGH code analysis flagged committed secret in PrismorSec/prismor
  4. HIGH code analysis flagged committed secret in PrismorSec/prismor
  5. HIGH code analysis flagged committed secret in PrismorSec/prismor
  6. HIGH code analysis flagged committed secret in PrismorSec/prismor
  7. HIGH code analysis flagged committed secret in PrismorSec/prismor
  8. HIGH code analysis flagged committed secret in PrismorSec/prismor

Each entry is one capability capture differing from the one before it — a review signal, not a verdict.