Caveat verdict
listenhub
Content-to-podcast/video/TTS/image conversion skill using proprietary ListenHub/Marswave API via local scripts; explicitly forbids direct API calls and mandates script-only interface, no signs of credential exfiltration or injection.
⚠ 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.
Permission integrity
credential_access
Findings (8)
Accesses shell history/config
SKILL.md · code · ~/.zshrc
Possible hardcoded credential
scripts/lib.sh · prose · downgraded · API_KEY="lh_sk_...
Popular HTTP library — network access
SKILL.md · code · Got
References sudo — requests elevated privileges
scripts/generate-image.sh · prose · downgraded · sudo
apt-get install — installs system packages
scripts/generate-image.sh · prose · downgraded · apt-get install
yum install — installs system packages
scripts/generate-image.sh · prose · downgraded · yum install
References agent configuration files
SKILL.md · prose · downgraded · CLAUDE.md
Base64 encoding/decoding
scripts/generate-image.sh · prose · downgraded · base64_decode
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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_incredential_access Is this flag fair?
Thanks — recorded.