ClawAudit verdict
agentverse-cli
Both Linux/macOS and Windows install commands execute remotely fetched scripts directly (`curl ... | bash`, `irm ... | iex`), which runs unvetted code from GitHub on the host machine without prior inspection.
โ 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.
Permission integrity
network_out
Findings (2)
Pipe-to-shell pattern (curl | sh) โ supply chain attack vector
SKILL.md ยท frontmatter ยท curl -fsSL https://raw.githubusercontent.com/loonghao/agentverse/main/install.sh
Pipe to bash โ executes piped content as shell commands
SKILL.md ยท frontmatter ยท | bash
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/E). Final tier capped at Caution โ cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
network_outnetwork_in Is this flag fair?
Thanks โ recorded.