Get a demo — 30 minutes →
Skill scan report

ASR

View on GitHub
35 Medium Automated analysis flagged 2 potential risk patterns.

What this skill does

Speech-to-text (ASR) implementation using the z-ai-web-dev-sdk

github/jjyaoao - Exfiltration Risk - 2.7k stars

ThreatsExfiltration Risk Third-Party Dependency Risk

Threat analysis

Exfiltration Risk1 finding
Third-Party Dependency Risk1 finding

Skill info

Namejjyaoao/asr
Registrygithub
Version5432566
PURLpkg:github/jjyaoao/HelloAgents@5432566?skill=asr
Stars2.7k

Assessments (2)

Exfiltration Risk1 finding HIGH
HIGH

Exfiltration Risk via local-llm-review

scripts/asr.ts

The script uses the z-ai-web-dev-sdk to send audio files (converted to base64) to an external service for transcription. This could potentially exfiltrate sensitive audio data to a third-party service
Third-Party Dependency Risk1 finding MEDIUM
MEDIUM

Third-Party Dependency Risk via local-llm-review

scripts/asr.ts

The script relies on the z-ai-web-dev-sdk, which is not a standard or well-known library. This introduces a risk if the SDK is not secure, contains vulnerabilities, or is not properly audited.

Badge

Add the Anomity scan badge for ASR to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/jjyaoao/asr/)
HTML
<a href="https://anomity.ai/skills/github/jjyaoao/asr/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

How Anomity governs this at runtime

Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.

Book a 30-minute demo to see your own skill inventory.

Methodology and disputes

Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of ASR? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok