Back to skill

Security audit

Elevenlabs Twilio Memory Bridge

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with medium confidence: the reported findings are considered purpose-aligned, though one scanner inspected only part of the artifact.

The verdict is benign, not a guarantee of no risk. Consider the medium confidence and partial scan coverage before installing; the manifest was malformed and some local references could not be resolved, so not all evidence is complete.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · README.md (reported line 75)May include surrounding context.

2. Configure environment

bash
cp .env.example .env
# Edit .env with your actual values

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · README.md (reported line 76)May include surrounding context.

bash
cp .env.example .env
# Edit .env with your actual values

Required secrets (generate before first run):

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · README.md (reported line 267)May include surrounding context.

md
[Service]
User=bridge
WorkingDirectory=/opt/elevenlabs-twilio-memory-bridge
EnvironmentFile=/opt/elevenlabs-twilio-memory-bridge/.env
ExecStart=/opt/elevenlabs-twilio-memory-bridge/venv/bin/uvicorn app:app --host 0.0.0.0 --port 8000
Restart=always

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 145)May include surrounding context.

  1. Hang up, call again — the agent remembers your previous interaction
  2. Add a memory via the API:
    bash
    curl -X POST http://localhost:8000/api/memory/PHONE_HASH \
      -H "Authorization: Bearer <your-admin-api-key>" \
      -H "Content-Type: application/json" \
      -d '{"fact": "Prefers to be called Mike"}'
    

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · app.py (reported line 77)May include surrounding context.

python
# ── Logging ─────────────────────────────────────────────────────────────────

logging.basicConfig(
    level=getattr(logging, LOG_LEVEL, logging.INFO),
    format="%(asctime)s | %(levelname)-7s | %(name)s | %(message)s",
    datefmt="%Y-%m-%dT%H:%M:%S",
)