registry / AI-agent capability abuse / @kryptosai/mcp-observatory / 1.48.2

@kryptosai/mcp-observatory@1.48.2

MCP security scanner and CI gate. Test, secure, and monitor MCP servers with attack simulation, schema drift detection, health scoring, and SARIF before agents depend on them.

AI Security Review

scanned 13d ago · by lpm-firewall-ai

Source shows explicit user-command mutation of MCP client configuration, which warrants a capability warning under the agent integration policy. The package's install hook does not itself mutate agent configuration without opt-in.

Static reason

One or more suspicious static signals were detected.; source matched previously finalized malicious package; routed for review; previous stored version diff introduced dangerous source

Trigger

A user runs the `protect` CLI command.

Impact

Client server launches are routed through the wrapper; no unconsented install-time agent configuration mutation was identified.

Mechanism

It updates server command and argument entries, backs up each configuration, then writes the modified file.

AI rationale

Evidence

dist/src/commands/handshake.jsdist/src/handshake.js.mcp.json

Decision evidence

public snapshot

AI called this Suspicious at 86.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

An explicit `protect` CLI command can rewrite discovered MCP client configuration files; this is a guarded agent configuration capability.
The configuration rewrite wraps server commands, saves a backup, and writes the modified configuration.
The postinstall hook skips CI and self-installs, and only proceeds for likely MCP projects.

Evidence against

Postinstall workflow creation requires `mcpObservatory.autoSetupCi=true` or an explicit environment opt-in.
The protected configuration operation is activated by the user invoking the `protect` command.

Behavioral surface

Source

ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell

Supply chain

HighEntropyStringsUrlStrings

ManifestNo manifest risk signals triggered.

scanned 126 file(s), 767 KB of source, external domains: 127.0.0.1, app.mcp-observatory.com, docs.oasis-open.org, github.com, img.shields.io, mcp-observatory-telemetry.kryptosai.workers.dev, mcp-observatory.com, registry.modelcontextprotocol.io, registry.smithery.ai, www.w3.org

Source & flagged code

10 flagged

package.jsonView file

Lines 86-126json

86 "docs/tool-call-receipts.md",

87 "examples/demo-mcp-server.mjs",

88 "examples/insecure-mcp-server",

89 "scripts/postinstall.mjs",

90 "schemas",

91 "docs/usage-learning.md",

92 "examples/usage-learning.mjs"

93 ],

94 "scripts": {

95 "build": "tsc -p tsconfig.json",

96 "cli": "tsx src/cli.ts",

97 "dashboard:build": "tsx scripts/build-dashboard.ts && tsx scripts/generate-server-pages.ts",

98 "dashboard:validate": "node scripts/validate-dashboard.mjs",

99 "traffic:smoke": "node scripts/traffic-quality-smoke.mjs",

100 "integration:real": "tsx scripts/run-real-server-matrix.ts",

101 "evaluate:permission-delta": "tsx scripts/evaluate-permission-delta-conformance.ts",

102 "evaluate:permission-delta:mcp-diff": "tsx scripts/run-mcp-diff-baseline.ts",

103 "safety-index": "tsx scripts/run-safety-index.ts",

104 "lint": "eslint .",

105 "prepack": "npm run build",

106 "postinstall": "node scripts/postinstall.mjs",

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg · L106

Medium

Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg · L106

107 "proof:refresh": "tsx scripts/refresh-proof-artifacts.ts",

108 "release:prep": "node scripts/release.mjs",

109 "certification:pr-body": "tsx scripts/print-certification-pr-body.ts",

110 "typecheck": "tsc --noEmit -p tsconfig.json",

111 "test": "vitest run",

112 "test:permission-delta-model": "vitest run tests/permission-delta-model.test.ts",

113 "test:coverage": "vitest run --coverage",

114 "validate:artifacts": "tsx scripts/validate-artifacts.ts",

115 "verify:packed-install": "node scripts/verify-packed-install.mjs",

116 "smoke": "npm run cli -- run --target tests/fixtures/sample-target-config.json && npm run cli -- diff tests/fixtures/sample-run-a.json tests/fixtures/sample-run-b.json",

117 "boundary:check": "node scripts/check-repository-boundary.mjs"

118 },

119 "keywords": [

120 "mcp",

121 "mcp-server",

122 "model-context-protocol",

123 "ai-agent",

124 "agent-security",

125 "ai-supply-chain",

126 "ai-tools",

dist/src/ci-issue.jsView file

Lines 1-21javascript

1import { execFile } from "node:child_process";

2import { mkdtemp, rm, writeFile } from "node:fs/promises";

High

Child Process

Package source references child process execution.

dist/src/ci-issue.jsView on unpkg · L1

3import { tmpdir } from "node:os";

dist/src/commands/demo.jsView file

Lines 1-31javascript

1import { createRequire } from "node:module";

2import path from "node:path";

3import { fileURLToPath } from "node:url";

4import { runTarget } from "../index.js";

dist/src/commands/test.jsView file

Lines 222-262javascript

222 }

223 else {

224 await maybeConvertPassingCheckToCi({

225 artifact,

226 target,

227 targetPath: options.target,

228 setupCi: conversionFlags.setupCi,

229 yes: conversionFlags.yes,

230

dist/src/checks/skill-scan.js#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 6

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

dist/src/checks/skill-scan.js#virtual:normalized:round1View on unpkg

dist/src/commands/helpers.jsView file

•matchType = normalized_sha256 matchedPackage = @kryptosai/mcp-observatory@1.36.4 matchedPath = dist/src/commands/helpers.js matchedIdentity = npm:[redacted]:1.36.4 similarity = 1.000 summary = normalized source hash matched finalized malicious source

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

dist/src/commands/helpers.jsView on unpkg

dist/src/risk-graph.jsView file

•matchType = normalized_sha256 matchedPackage = @kryptosai/mcp-observatory@1.36.4 matchedPath = dist/src/risk-graph.js matchedIdentity = npm:[redacted]:1.36.4 similarity = 1.000 summary = normalized source hash matched finalized malicious source

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

dist/src/risk-graph.jsView on unpkg

dist/src/utils/failure-diagnosis.jsView file

•matchType = normalized_sha256 matchedPackage = @kryptosai/mcp-observatory@1.36.4 matchedPath = dist/src/utils/failure-diagnosis.js matchedIdentity = npm:[redacted]:1.36.4 similarity = 1.000 summary = normalized source hash matched finalized malicious source

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

dist/src/utils/failure-diagnosis.jsView on unpkg

dist/src/usage/review.jsView file

•matchType = previous_version_dangerous_delta matchedPackage = @kryptosai/mcp-observatory@1.45.5 matchedIdentity = npm:[redacted]:1.45.5 similarity = 0.891 summary = stored previous version shares package body but lacks this dangerous source file

Critical

Previous Version Dangerous Delta

This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.

dist/src/usage/review.jsView on unpkg

Source & flagged code

10 flagged · loading source

package.jsonView file

•scripts.postinstall = node scripts/postinstall.mjs

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

•scripts.postinstall = node scripts/postinstall.mjs

Medium

Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg

dist/src/ci-issue.jsView file

1import { execFile } from "node:child_process"; L2: import { mkdtemp, rm, writeFile } from "node:fs/promises";

High

Child Process

Package source references child process execution.

dist/src/ci-issue.jsView on unpkg · L1

Findings

1 Critical8 High5 Medium4 Low

CriticalPrevious Version Dangerous Deltadist/src/usage/review.js

HighInstall Time Lifecycle Scriptspackage.json

HighChild Processdist/src/ci-issue.js

HighShell

HighRuntime Package Installdist/src/commands/test.js

HighSemantic Analysis Limiteddist/src/checks/skill-scan.js#virtual:normalized:round1

HighKnown Malware Source Similaritydist/src/commands/helpers.js

HighKnown Malware Source Similaritydist/src/risk-graph.js

HighKnown Malware Source Similaritydist/src/utils/failure-diagnosis.js

MediumAmbiguous Install Lifecycle Scriptpackage.json

MediumDynamic Requiredist/src/commands/demo.js

Affected versions and remediation

This report applies to @kryptosai/mcp-observatory@1.48.2.

See all versions of @kryptosai/mcp-observatory for other recorded verdicts.

Review the evidence and your use of @kryptosai/mcp-observatory@1.48.2 before allowing it. Restrict the permissions described in this report.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.

Evidence last updated: 2026-10-09 16:54:21.581Z (UTC).

Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Affected versions and remediation

Runtime surface

Behavioral surface

Source & flagged code