@twilio-alpha/mcp
The AI review rates the findings as likely false positive, but the risk score (100/100) still counts them.
Analysis record
- Analysed
- 8 months ago 10 March 2026
- Version
- v0.7.0
- Detail
- Full list
Evidence ledger
Ranked by severity ยท findings with a source location link to the code viewer
YARA Rule Matches
11 rules| Severity | Rule | Hits | Files | Metadata |
|---|---|---|---|---|
| HIGH | postinstall crypto operations Cryptographic operations detected | 10 | twilio-oai/spec/yaml/twilio_video_v1.yamltwilio-oai/spec/json/twilio_studio_v2.jsontwilio-oai/spec/yaml/twilio_studio_v1.yaml +7 more | Risky Plugins Authors FP 30% |
| HIGH | DebuggerStatementsShouldNotBeUsed The debugger statement can be placed anywhere in procedures to suspend execution. Using the debugger statement is similar to setting a breakpoint in the code. By definition such statement must absolutely be removed from the source code to prevent any unexpected behavior or added vulnerability to attacks in production. For more information checkout the CWE-489 (https://cwe.mitre.org/data/definitions/489.html) advisory. | 2 | twilio-oai/spec/yaml/twilio_flex_v1.yamltwilio-oai/spec/json/twilio_flex_v1.json | FP 10% |
| HIGH | postinstall persistence mechanism Persistence mechanism detected | 14 | twilio-oai/spec/json/twilio_messaging_v1.jsontwilio-oai/spec/yaml/twilio_proxy_v1.yamltwilio-oai/spec/yaml/twilio_messaging_v1.yaml +11 more | Risky Plugins Authors FP 20% |
| HIGH | postinstall system command System command execution detected | 61 | README.mdtwilio-oai/spec/yaml/twilio_preview.yamlbuild/tools/uploadFunction.js +58 more | Risky Plugins Authors FP 10% |
| HIGH | postinstall file manipulation File system manipulation detected | 83 | twilio-oai/spec/json/twilio_lookups_v1.jsontwilio-oai/spec/json/twilio_marketplace_v1.jsontwilio-oai/spec/yaml/twilio_frontline_v1.yaml +80 more | Risky Plugins Authors FP 20% |
| HIGH | postinstall environment access Environment variable access detected | 49 | twilio-oai/spec/yaml/twilio_studio_v1.yamltwilio-oai/spec/yaml/twilio_ip_messaging_v2.yamltwilio-oai/spec/yaml/twilio_bulkexports_v1.yaml +46 more | Risky Plugins Authors FP 40% |
| HIGH | postinstall network communication Network communication detected | 76 | twilio-oai/spec/json/twilio_flex_v1.jsontwilio-oai/spec/yaml/twilio_video_v1.yamltwilio-oai/spec/json/twilio_ip_messaging_v1.json +73 more | Risky Plugins Authors FP 30% |
| HIGH | credential env files Environment configuration file path detected | 2 | twilio-oai/spec/yaml/twilio_serverless_v1.yamltwilio-oai/spec/json/twilio_serverless_v1.json | Risky Plugins Authors FP 10% |
| HIGH | postinstall file download File download activity detected | 96 | twilio-oai/spec/json/twilio_proxy_v1.jsontwilio-oai/spec/yaml/twilio_supersim_v1.yamltwilio-oai/spec/json/twilio_conversations_v1.json +93 more | Risky Plugins Authors FP 30% |
| HIGH | postinstall obfuscation Code obfuscation techniques detected | 20 | twilio-oai/spec/json/twilio_intelligence_v2.jsontwilio-oai/spec/yaml/twilio_taskrouter_v1.yamltwilio-oai/spec/json/twilio_taskrouter_v1.json +17 more | Risky Plugins Authors FP 20% |
| HIGH | postinstall registry modification Windows registry modification detected | 2 | twilio-oai/spec/yaml/twilio_messaging_v1.yamltwilio-oai/spec/json/twilio_messaging_v1.json | Risky Plugins Authors FP 30% |
Finding Categories
YARA Rules Matched
11 rules(415 hits)MCP Server Analysis
MCP servers expose tools and resources to AI assistants. Unlike browser extensions, they run as standalone processes with direct system access. Tool definitions are analyzed for prompt injection, data exfiltration, and tool poisoning patterns.
AI Security Report
AI Security Review
Evidence context: threat category none; evidence quality weak.
The CRITICAL risk score (100) for this Twilio API wrapper is a statistical anomaly driven by noise rather than active threats. The analysis detected 3,770 total findings, but 3,155 are generic Indicators of Compromise (IoCs). This volume strongly suggests the presence of bundled dependencies or minified code triggering false positives on patterns like IPv6 fragments ('::', '::1') and loopback addresses ('0.0.0.0', '127.0.0.1'), which are benign in local server contexts.
The 85 'tool-poisoning' findings also appear to be false positives. Given the package's purposeโto expose Twilio APIsโthese likely represent legitimate tool definitions (e.g., tools named 'Send Message' or 'List Calls') with standard descriptions intended for human developers, rather than hidden directives aimed at manipulating the AI agent. There is no evidence of credential harvesting targeting system secrets (like .aws or .ssh), nor are there exfiltration patterns combining credential access with unknown network destinations. This looks like a standard, powerful API wrapper tripped up by hypersensitive generic scanners.
Key Reasons
- Massive IoC count (3155) indicative of bundled dependencies or minified code, not malicious infrastructure
- Tool-poisoning findings (85) likely map to standard Twilio API tool definitions
- No evidence of environment variable exfiltration targeting system secrets
- Risk score 100/100 is consistent with known score-inflation false positive patterns
False Positive Considerations
- IoC Extractor false positives (IPv6 fragments, loopback addresses)
- Scanner confusion between tool definitions and tool poisoning
Reviewed 2026-04-12; recommended action: suppress false positive; model confidence 60%.
Source Code Not Available
Source code is not available for this version of the extension.
About This Extension
Frequently Asked Questions
Similar Extensions
Related extensions from the same publisher or marketplace