SKILLEMALL.ai
GitHub ↗ RU Sign in

BD elevenlabs-twilio-memory-bridge

FastAPI personalization webhook that adds persistent caller memory and dynamic context injection to ElevenLabs Conversational AI agents on Twilio. No audio proxying, file-based persistence, OpenClaw compatible.

ClawHub Agent Skills author: Britrik v1.2.1 MIT-0 15 files body ≈ 1 305 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationInfrastructureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
78/100
safety, quality, tests
Safety 60%
84
Quality 40%
69
Run on models
none yet
Process rating
D
43/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Instruction override medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 4

✓ No critical or high findings

Medium and low: 4
  • medium Exfiltration net-redirectable-api-key app.py:58
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Instruction override en-fake-system-prompt README.md:42
    Fake system prompt injected into content (documentation of a security skill)
    5. It returns personalized context (system prompt override + dynamic variables)
    security skill
  • medium Instruction override en-fake-system-prompt SKILL.md:74
    Fake system prompt injected into content (documentation of a security skill)
    When a call arrives on your Twilio number, ElevenLabs' native integration triggers this webhook. The bridge looks up the caller's history, loads long-term memory facts and daily context notes, combine
    security skill
  • low Exfiltration read-dotenv README.md:69
    Reads a .env file (documentation of a security skill)
    cp .env.example .env
    security skill

Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 43/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 100Steps. 36 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1305 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +2Single-language instructions
  • +3Description length 210: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 36 items
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
The skill matches its stated memory-bridge purpose, but it needs Review because it persists sensitive caller context and injects stored text into agent system prompts, with encryption optional.
LLM: suspicious (high) · VirusTotal: · 10 Sept 2026