Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward audio transcription helper that sends user-selected audio to a disclosed MOSS/MOSI transcription API and saves the returned transcript locally.
Install only if you intend to use the MOSS/MOSI remote transcription service and are comfortable sending the selected audio, URLs, or base64 audio data to that provider. Avoid submitting confidential, regulated, or third-party recordings unless you have authorization and understand the provider's retention and privacy terms.
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.
}
try:
r = requests.post(TRANSCRIBE_URL, headers=headers, json=payload, timeout=args.timeout)
except requests.RequestException as e:
fail(f"request failed: {e}")
The skill invokes a Python script that can read local files, write output files, access environment variables for API keys, and make outbound network requests, but it does not declare any explicit tool scope or permissions. This weakens enforcement and transparency, increasing the chance that an agent platform grants broader access than users expect or that risky operations occur without clear consent boundaries.
The skill processes potentially sensitive audio and sends it to an external API endpoint, but the description does not clearly warn users that their audio content and derived transcription data will leave the local environment. In the context of meetings, interviews, and multi-speaker conversations, this can expose confidential, personal, or regulated information without sufficiently informed user consent.
The skill transmits raw audio or local file contents to an external third-party transcription endpoint, and this may include sensitive conversations, personal data, or regulated content. In a skill context, users may invoke local-file transcription without fully appreciating that the content leaves the local environment, so the absence of an explicit warning/consent step increases privacy and compliance risk.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
}
try:
r = requests.post(TRANSCRIBE_URL, headers=headers, json=payload, timeout=args.timeout)
except requests.RequestException as e:
fail(f"request failed: {e}")
Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.
out_path = Path(args.out)
out_path.parent.mkdir(parents=True, exist_ok=True)
out_path.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
segs = normalize_segments(data)
No suspicious patterns detected.