ClawAudit verdict
transcription-speech-to-text-hebrew
This skill transparently discloses that it sends audio files and the TEXTOPS_API_KEY to TextOps servers for transcription, includes explicit prompt-injection guardrails for transcription output, and all described behavior matches its stated audio transcription purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
network_out
Findings (4)
Possible hardcoded credential
SKILL.md · frontmatter · api_key: "TEXTOPS_API_KEY
Accesses shell history/config
SKILL.md · prose · downgraded · ~/.zshrc
subprocess execution — runs system commands from Python
scripts/download_audio.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
scripts/transcribe.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_access Is this flag fair?
Thanks — recorded.