agent-nervous-system-mcp@1.3.0
Shared context MCP for AI agents - append-only, zero config, auto-detect
AI Security Review
scanned 3h ago · by lpm-firewall-aiThe manifest activates a postinstall setup that silently changes every detected agent configuration in non-interactive installs. This establishes unconsented AI-agent control-surface mutation and warrants blocking.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
The package postinstall hook runs during installation with non-interactive stdin.
Impact
Agent configurations are changed without an affirmative selection, enabling this server in those agents after restart.
Mechanism
The setup detects agent configuration files and writes an MCP server entry to each selected file; non-interactive execution selects all detected agents.
Policy narrative
During installation, the postinstall hook detects installed AI agents. If stdin is non-interactive, it selects all detected agents and writes this server into their configuration files without asking the user. This is an unconsented change to agent control settings.
AI rationale
The manifest activates a postinstall setup that silently changes every detected agent configuration in non-interactive installs. This establishes unconsented AI-agent control-surface mutation and warrants blocking.
Evidence
package.jsonscripts/postinstall.js~/.claude.json~/.config/Claude/claude_desktop_config.json
Decision evidence
public snapshotAI identified this as a dangerous AI-agent capability at 97.0% confidence with low false-positive risk.
Evidence for policy risk
- package.json runs scripts/postinstall.js during installation.
- The install hook detects and selects all configured agents when stdin is non-interactive, then writes their configuration files.
- The setup adds this MCP server to detected agent configurations without an affirmative choice in non-interactive mode.
Evidence against
Behavioral surface
ChildProcessFilesystemShell
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 unpkg14"postinstall": "node scripts/postinstall.js"
},
"keywords": ["mcp", "shared-context", "agent-memory", "ai", "common-context"],
"author": "",
"license": "MIT",
"dependenci
High
Suspicious Lifecycle Evidence
package.json runs scripts/postinstall.js during installation.
package.jsonView on unpkg · L14•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 unpkgscripts/postinstall.jsView file
Findings
1 Critical5 High2 Medium4 Low
CriticalAi Agent Control Hijackscripts/postinstall.js
HighInstall Time Lifecycle Scriptspackage.json
HighPrevious Version Dangerous Deltascripts/postinstall.js
HighSuspicious Lifecycle Evidencepackage.json
HighSuspicious Lifecycle Evidencescripts/postinstall.js
HighSuspicious Lifecycle Evidencescripts/postinstall.js
MediumAmbiguous Install Lifecycle Scriptpackage.json
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
Affected versions and remediation
This report applies to agent-nervous-system-mcp@1.3.0.
See all versions of agent-nervous-system-mcp for other recorded verdicts.
- Avoid installing agent-nervous-system-mcp@1.3.0. Remove it from direct dependencies and check your lockfile for transitive copies.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
- If this version ran, investigate the affected machine and build environment. Rotate credentials it could access and rebuild from a trusted environment.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.