agent-nervous-system-mcp@1.0.1
Shared context MCP for AI agents - append-only, zero config, auto-detect
AI Security Review
scanned 10h ago · by lpm-firewall-aiThe package’s automatic postinstall mutation reaches multiple user-level AI-agent configurations and enables the package as an agent server without an explicit setup action. This meets the blocking policy for unconsented install-time mutation of a broad AI-agent control surface.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
Installing the package runs its postinstall hook.
Impact
Supported agents can load and launch this MCP server without the user explicitly configuring it.
Mechanism
The hook writes a common-context server entry into each targeted agent configuration when its file or parent directory exists.
Policy narrative
During package installation, the postinstall hook checks for configuration files or directories for several AI agents and writes a common-context MCP entry that launches this package. The hook does not require explicit user setup or consent before changing those agent configurations.
AI rationale
The package’s automatic postinstall mutation reaches multiple user-level AI-agent configurations and enables the package as an agent server without an explicit setup action. This meets the blocking policy for unconsented install-time mutation of a broad AI-agent control surface.
Evidence
package.jsonscripts/postinstall.js~/.config/claude/claude_desktop_config.json~/.cursor/mcp.json~/.config/opencode/opencode.json~/.codeium/windsurf/mcp_config.json
Decision evidence
public snapshotAI identified this as a dangerous AI-agent capability at 94.0% confidence with low false-positive risk.
Evidence for policy risk
- package.json runs scripts/postinstall.js during installation.
- The installer targets global configuration files for several AI agents, including Claude Desktop, Cursor, OpenCode, and Windsurf.
- The entries added to those configurations invoke this package’s command.
- The installer modifies an agent configuration whenever its file or parent directory exists; no explicit setup or consent check guards the write.
- The installer writes the modified configuration and replaces the common-context entry.
Evidence against
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 unpkg13"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 · L13•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
HighSuspicious Lifecycle Evidencepackage.json
HighAi Review Evidencescripts/postinstall.js
HighAi Review Evidencescripts/postinstall.js
HighAi Review 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@1.0.1.
See all versions of agent-nervous-system-mcp for other recorded verdicts.
- Avoid installing agent-nervous-system-mcp@1.0.1. 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.