MCP Observatory
github analyzed 51a7464

EvoMap/evolver

github

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

maintainer
EvoMap
license
GPL-3.0
first seen
2026-05-22
last seen
2026-06-13
releases · 30d
34
short id
risk100/100 · heuristic grade
E critical
  • vulnerabilitiesattested+50
  • capability exposureinferred+35
  • recent driftinferred+20
  • trust mitigatorsmixed−3

attestedinferredmixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

graded 7m ago · see ecosystem CVEs →

capability exposuregrade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities6 CVEs · grade factor +50
CRITICAL
Command Injection via `execSync` in `_extractLLM()` function allows Remote Code Execution EPSS 1% CVE-2026-42076 affects ["< 1.69.3"]
HIGH
Validator sandbox allowlist permits `npm`/`npx`, yielding RCE from Hub-delivered validation tasks vi… affects ["<= 1.70.0-beta.4"]
HIGH
Path traversal in `evolver fetch` default-branch `safeId` allows Hub-controlled overwrite of project… affects ["<= 1.70.0-beta.4"]
HIGH
Path Traversal via `--out` flag in `fetch` command allows Arbitrary File Write EPSS 0% CVE-2026-42075 affects ["< 1.69.3"]
MEDIUM
Unbounded request body in proxy /asset/submit causes persistent disk-exhaustion DoS affects ["<= 1.70.0-beta.4"]
MEDIUM
Prototype Pollution via `Object.assign()` in mailbox store operations EPSS 0% CVE-2026-42077 affects ["< 1.69.3"]
tool safety1 findings · grade factor +0
  1. highdangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (/tmp/obs-code-dyPJdK/EvoMap-evolve

skills & danger signalsgithub-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 51a7464 · analyzer v17 · 23h ago

skills & prompt files 1

other grade factorsevidence elsewhere
embed badgereadme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:EvoMap/evolver/badge.svg)](https://mcpobservatory.com/servers/github:EvoMap/evolver/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of EvoMap.