common-context-mcp@1.0.0
Shared context MCP for AI agents - append-only, zero config, auto-detect
AI Security Review
scanned 14h ago · by lpm-firewall-aiThe postinstall hook performs unconsented changes across multiple AI agent control surfaces, registering a server that gives connected agents persistent work-context instructions. This supports blocking for AI agent control hijacking; the reviewed source does not establish network exfiltration.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
Installing the npm package runs its postinstall hook.
Impact
AI agent configurations are altered without a separate affirmative setup action, enabling the package's server in those clients and directing them to persist work context locally.
Mechanism
The hook checks several agent configuration locations and writes an MCP server entry when a configuration or its directory exists. The server's instructions direct agents to save work details as they proceed.
Policy narrative
On npm installation, the package automatically edits existing user-level configurations for multiple AI agent clients to register its MCP server. That server instructs connected agents to load shared context and save work details. The source shows no separate consent check for this configuration change.
AI rationale
The postinstall hook performs unconsented changes across multiple AI agent control surfaces, registering a server that gives connected agents persistent work-context instructions. This supports blocking for AI agent control hijacking; the reviewed source does not establish network exfiltration.
Evidence
package.jsonscripts/postinstall.jsdist/index.js~/.config/claude/claude_desktop_config.json~/.cursor/mcp.json~/.config/opencode/opencode.json~/.codeium/windsurf/mcp_config.json~/.vscode/mcp.json~/.continue/config.json~/.shared-context.json
Decision evidence
public snapshotAI identified this as a dangerous AI-agent capability at 90.0% confidence with low false-positive risk.
Evidence for policy risk
- The package runs scripts/postinstall.js automatically after installation.
- The hook targets user-level configuration files for six AI agent clients.
- When a target configuration or agent directory exists, the hook adds the package's MCP entry and writes the configuration without a consent check.
- The registered server tells connected agents to load shared context and save work details frequently.
- The server stores shared context in a file under the user's home directory.
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
The package runs scripts/postinstall.js automatically after 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 common-context-mcp@1.0.0.
See all versions of common-context-mcp for other recorded verdicts.
- Avoid installing common-context-mcp@1.0.0. 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.