ClawAudit verdict
minimax-tts
minimax-speech
The skill uses the MiniMax API for text-to-speech functionality, with no evidence of malicious behavior.
⚠ 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.
Findings (2)
Instruction-prose smuggling shape detected: collects a sensitive target ("credential") and emits it outward ("POST"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.
SKILL.md · 1. **Install dependencies.** Run `pip install requests` in the environment that will execute the script. The CLI talks to MiniMax's REST API, so you only need t
Python os.getenv — reads environment variable
scripts/minimax_tts.py · prose · downgraded · os.getenv(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.