ClawAudit verdict

hugging-face-cli

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill uses package_install capability.

⚠ 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.

85
security
60
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("environment variable") and emits it outward ("upload"). 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 · If authentication fails or the token is missing, instruct the user to: 1. Go to https://huggingface.co/settings/tokens 2. Create a new token — there are two per

Pattern match medium

Accesses shell history/config

SKILL.md · prose · downgraded · ~/.zshrc

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: [HF_TOKEN]). Requires 1 system binary.

package_install

Is this flag fair?

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