@kryptosai/mcp-observatory@1.43.1
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 14d ago · by lpm-firewall-aiSource inspection found an explicitly invoked agent configuration capability, which warrants a warning under the agent capability policy. The postinstall setup path is gated by explicit opt-in, and no concrete attack behavior was established.
Decision evidence
public snapshot- The postinstall hook exits for CI and performs setup only when auto-setup is explicitly enabled.
- The `protect` command can wrap MCP server entries across discovered client configuration files when explicitly invoked.
- Wrapping rewrites server commands and arguments and creates a backup of each configuration file.
- The inspected install hook does not automatically rewrite agent client configurations.
- No source evidence established credential collection, exfiltration, or an active attack.
Source & flagged code
10 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references child process execution.
dist/src/ci-issue.jsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @kryptosai/mcp-observatory@1.43.1.
See all versions of @kryptosai/mcp-observatory for other recorded verdicts.
- Review the evidence and your use of @kryptosai/mcp-observatory@1.43.1 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.