ClawAudit verdict

obsidian-search

45
๐ŸŸ  Risky
Significant concerns โ€” only install if you understand the risks

The skill uses a third-party server (Obvec) for semantic search, which may pose a risk if not properly configured. However, the token used for access seems to be read-only and has a limited scope.

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. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

100
security
100
transparency
90
maintenance

Findings (1)

Coarse signal โ€” prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("Paste"). Phrased as prose with no trigger tokens โ€” 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 ยท 1. **Sign up** at [obsidian.10xboost.org](https://obsidian.10xboost.org) with Google 2. **Connect your Obsidian vault** โ€” follow the setup guide to sync your no

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

Is this flag fair?

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