ClawHub
Back to skill

Security audit

Telegram Import

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed local importer for Telegram messages into a vector database, with privacy-sensitive data handling that users should understand before running it.

Install only if you intend to index the Telegram database named in the skill. Treat the resulting LanceDB folder as sensitive because it contains searchable message text and sender/group metadata, restrict filesystem access to it, and make sure the localhost embedding service is one you control and trust.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly documents importing Telegram message text plus rich metadata (group names, sender identifiers, keywords, reply status, and flags) into a vector database, but provides no warning that this may ingest sensitive personal or confidential content. In this context, the omission is security-relevant because vectorized chat archives can become broadly queryable and harder to govern, increasing the risk of privacy leakage, unauthorized retention, or secondary misuse of communications data.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The script sends raw Telegram message text to an HTTP embedding service, which is an external process boundary even if it is bound to localhost. That can expose sensitive message contents to another service without clear consent, minimization, or safeguards, and the local-only transport assumption may not hold if the endpoint is proxied, logged, or reconfigured.

External Transmission

Medium
Category
Data Exfiltration
Content
def embed_texts(texts, timeout=120):
    """Call LM Studio embedding API. Returns list of float[EMBED_DIM] vectors."""
    resp = requests.post(
        LM_URL,
        json={"model": LM_MODEL, "input": texts},
        timeout=timeout,
Confidence
84% confidence
Finding
requests.post( LM_URL, json=

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.