ClawAudit verdict

aura

aura-a2a-marketplace

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

The skill instructs the agent to autonomously register a new account and receive an API key that grants spending power over credits, without explicit per-action human approval; while the content includes security warnings, the autonomous registration + credential-issuance flow represents a real financial action initiated by the agent.

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.

75
security
70
transparency
70
maintenance

Findings (2)

Pattern match medium

Sets world-executable permissions

SKILL.md ยท code ยท chmod 700

Pattern match medium

Base64 encoding/decoding

SKILL.md ยท code ยท BASE64_ENCODE

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: AURA_API_KEY). Requires 1 system binary. (1 elevated: curl).

network_outcredential_accessnetwork_indata_encoding

Is this flag fair?

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