Caveat verdict

audio-analyzer

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Audio transcription and speaker identification skill using AssemblyAI/Whisper/Gemini APIs; explicitly states voice embeddings are stored locally and never sent externally, with transparent data handling disclosures.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

58
security
70
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Pattern match medium

References child_process — can spawn system processes

scripts/analyze.js · prose · downgraded · child_process

Pattern match medium

Dynamic import() — loads module at runtime

scripts/analyze.js · prose · downgraded · import('

Pattern match medium

subprocess execution — runs system commands from Python

scripts/voiceprint.py · prose · downgraded · subprocess.run(

Pattern match low

Accesses sensitive environment variables

scripts/analyze.js · prose · downgraded · process.env.ASSEMBLYAI_API_KEY

Pattern match low

Popular HTTP library — network access

scripts/package-lock.json · prose · downgraded · node-fetch

Pattern match low

Python os.environ.get — reads environment variable

scripts/voiceprint.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.

package_install

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API