Caveat verdict

tos-vectors

volcengine-tos-vectors-skills

45
๐ŸŸ  Risky
Significant risk patterns flagged โ€” automated deep scan, not behavioral proof.

The skill manages vector storage and similarity search using TOS Vectors service, sending data to external hosts for authentication and verification. However, it seems to be for a legitimate purpose.

โš  Flagged for review โ€” coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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

90
security
60
transparency
70
maintenance

Findings (1)

Pattern match medium

Python os.getenv โ€” reads environment variable

SKILL.md ยท code ยท os.getenv(

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

network_incredential_access

Is this flag fair?

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