transcribe
What this skill does
Transcribe audio files to text with optional diarization and known-speaker hints using OpenAI's API.
github/openai - Secrets Exfiltration - 24.7k stars
Threat analysis
Skill info
pkg:github/openai/skills@49f948f?skill=transcribeAssessments (2)
Secrets Exfiltration
Secrets Exfiltration via local-llm-review
scripts/transcribe_diarize.py
The script uses `os.getenv('OPENAI_API_KEY')` to retrieve the API key, but there is no validation or obfuscation of the key. If the script is run in an environment where the key is exposed (e.g., in lInsecure Default Behavior
Insecure Default Behavior via local-llm-review
scripts/transcribe_diarize.py
The script does not enforce strict input validation for audio files. It uses `MAX_AUDIO_BYTES` to limit file size, but there is no explicit check to ensure that the file is not being uploaded to an exBadge
Add the Anomity scan badge for transcribe to your README.
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 transcribe? Report an issue or request a rescan.
