registry / agent-nervous-system-mcp / 1.1.0
agent-nervous-system-mcp@1.1.0
Shared context MCP for AI agents - append-only, zero config, auto-detect
AI Security Review
scanned 4h ago · by lpm-firewall-aiThe automatic, broad configuration of detected agents creates a first-party agent extension lifecycle risk. The inspected source did not establish unconsented prompt or tool-content export, credential theft, or another concrete attack.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
Installing the package when npm runs its postinstall hook; noninteractive installs select all detected agents.
Impact
Agent configuration is changed and the new MCP is enabled for those agents. This warrants a warning because the noninteractive setup applies broadly without a per-agent prompt; no further attack impact was established.
Mechanism
The hook adds the MCP command to selected agent configuration files. Its server instructions then direct agents to use the shared-context tools.
AI rationale
The automatic, broad configuration of detected agents creates a first-party agent extension lifecycle risk. The inspected source did not establish unconsented prompt or tool-content export, credential theft, or another concrete attack.
Evidence
package.jsonscripts/postinstall.jsdist/index.js
Decision evidence
public snapshotAI called this Suspicious at 90.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The package runs scripts/postinstall.js after installation.
- The hook detects agent configuration files in the user's home directory.
- In noninteractive installs, it selects every detected agent and writes updated configuration files.
- The runtime presents a workflow that directs agents to use its shared-context tools.
- Shared context is stored in a home-directory file; no network transfer was identified in the inspected runtime.
Evidence against
- The inspected runtime stores shared context locally, and searches found no network or child-process calls in its entrypoint.
Behavioral surface
Filesystem
HighEntropyStrings
Source & flagged code
7 flagged · loading sourcepackage.jsonView file
•scripts.postinstall = node scripts/postinstall.js
High
Install Time Lifecycle Scripts
Package defines install-time lifecycle scripts.
package.jsonView on unpkg•scripts.postinstall = node scripts/postinstall.js
Medium
Ambiguous Install Lifecycle Script
Install-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkg13"postinstall": "node scripts/postinstall.js"
},
"keywords": ["mcp", "shared-context",
Medium
Suspicious Lifecycle Evidence
The package runs scripts/postinstall.js after installation.
package.jsonView on unpkg · L13scripts/postinstall.jsView file
Findings
1 Critical1 High6 Medium4 Low
CriticalAi Agent Control Hijackscripts/postinstall.js
HighInstall Time Lifecycle Scriptspackage.json
MediumAmbiguous Install Lifecycle Scriptpackage.json
MediumStructural Risk Force Deep Review
MediumSuspicious Lifecycle Evidencepackage.json
MediumAi Review Evidencescripts/postinstall.js
MediumAi Review Evidencescripts/postinstall.js
MediumAi Review Evidencescripts/postinstall.js
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
Affected versions and remediation
This report applies to agent-nervous-system-mcp@1.1.0.
See all versions of agent-nervous-system-mcp for other recorded verdicts.
- Review the evidence and your use of agent-nervous-system-mcp@1.1.0 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.