ClawAudit verdict
glmv-grounding
The skill executes a bash script and uses the executionSinkDetected flag, which could potentially be used for malicious purposes.
⚠ 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
package_install
Findings (4)
subprocess execution — runs system commands from Python
scripts/utils_video.py · prose · downgraded · subprocess.run(
Python os.getenv — reads environment variable
scripts/glm_grounding_cli.py · prose · downgraded · os.getenv(
Base64 encoding/decoding
scripts/utils_boxes.py · prose · downgraded · base64-encode
Python shutil file operation — copies/moves/deletes files
scripts/utils_video.py · prose · downgraded · shutil.copy(
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
Requires 2 environment variables. (1 sensitive: ZHIPU_API_KEY).
credential_accesspackage_install Is this flag fair?
Thanks — recorded.