Caveat verdict

swarm-platform

18
🔴 Dangerous
High-risk patterns flagged for review — automated deep scan, not behaviorally verified.

The skill instructs the agent to curl 10 sub-modules from swarmprotocol.org and save them as executable markdown, then read and follow those externally-controlled instructions - a concrete remote instruction injection pattern where future agent behavior is determined by an untrusted external server.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

55
security
70
transparency
90
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Findings (1)

Pattern match critical

Recursive delete from root or home — destructive command

SKILL.md · code · rm -rf ~

Permissions & capabilities

No declared permissions — minimal attack surface.

network_out

Is this flag fair?

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