registry / @kryptosai/mcp-observatory / 1.50.1
@kryptosai/mcp-observatory@1.50.1
Free, MIT-licensed MCP security testing from ClearFrame. Scan, audit, compare and review MCP evidence locally; continue in ClearFrame CLI or Mac.
AI Security Review
scanned 1d ago · by lpm-firewall-aiSource inspection found a postinstall helper gated against CI and self-installs, with workflow creation requiring an explicit setting and using non-overwriting file creation. Telemetry is opt-in, while MCP config protection is user-invoked; the scanner flags did not establish malicious behavior.
Static reason
One or more suspicious static signals were detected.; source matched previously finalized malicious package; routed for review
Trigger
Install may print setup guidance; workflow creation requires an explicit setup setting. Telemetry requires affirmative enablement.
Impact
No confirmed harmful impact was identified; enabled telemetry can send product and identifying metadata to its configured endpoint.
Mechanism
The installer checks project and CI context, and creates a workflow only when auto-setup is enabled. Telemetry checks the saved or explicit preference before collecting or sending events.
AI rationale
Source inspection found a postinstall helper gated against CI and self-installs, with workflow creation requiring an explicit setting and using non-overwriting file creation. Telemetry is opt-in, while MCP config protection is user-invoked; the scanner flags did not establish malicious behavior.
Evidence
.github/workflows/mcp-observatory.yml
Network endpoints1
mcp-observatory-telemetry.kryptosai.workers.dev
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The postinstall hook exits for CI and self-installs, and only creates a workflow when an explicit environment or package setting enables setup; it leaves existing workflows untouched.
- Telemetry requires affirmative opt-in before collection or delivery. Its configured endpoint receives events only after telemetry is enabled.
- MCP config protection is exposed through an explicit CLI command; no install-time config rewrite was found.
- Reviewed entrypoint, runtime, install, and dependency source paths; no concrete attack behavior was identified.
- These dependency excerpts show MCP task request pass-through and status checks, OAuth URL/resource validation and error formatting, and CLI argument, error, and subprocess utilities.
- These CLI helpers filter hidden commands and initialize option flags and required-value metadata.
Evidence against
- The package defines a postinstall hook and includes code that can create a project CI workflow when explicitly enabled.
- Telemetry can include identifying machine and repository details, and its endpoint can be configured.
Behavioral surface
Source & flagged code
9 flagged · loading sourcepackage.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 unpkgdist/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 · L1Findings
8 High5 Medium4 Low
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
MediumNetwork
MediumEnvironment Vars
Affected versions and remediation
This report applies to @kryptosai/mcp-observatory@1.50.1.
See all versions of @kryptosai/mcp-observatory for other recorded verdicts.
- Review the evidence and your use of @kryptosai/mcp-observatory@1.50.1 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: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.