ClawAudit verdict

halocard-virtualcards

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

The skill seems to be related to payment processing and requires a specific token. However, its behavior and potential risks are not entirely clear.

⚠ 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.

100
security
80
transparency
70
maintenance

Findings (1)

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("environment variable") and emits it outward ("paste"). 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 · 1. Ask the user to sign up: https://secure.halocard.co/enter 2. Ask the user to copy paste an API token: https://secure.halocard.co/dashboard 3. Store it as `HA

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: HALOCARD_TOKEN).

Is this flag fair?

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