ClawAudit verdict
superclaw
superclaw-skills
A curated collection of 14 workflow discipline skills (TDD, debugging, code review, planning) with no concerning capabilities and no executable content beyond standard install instructions.
⚠ 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.
Findings (8)
<script> tag in markdown — potential code injection
brainstorming/visual-companion.md · prose · downgraded · <script>
Instructs covert action — may act without user awareness
subagent-driven-development/implementer-prompt.md · code · silently
Accesses system credential store
systematic-debugging/SKILL.md · prose · downgraded · Keychain
References agent configuration files
using-git-worktrees/SKILL.md · code · CLAUDE.md
References child_process — can spawn system processes
writing-skills/render-graphs.js · prose · downgraded · child_process
Uses exec() — may execute shell commands
writing-skills/render-graphs.js · prose · downgraded · exec(
Opens WebSocket connection
brainstorming/scripts/helper.js · prose · downgraded · WebSocket
Popular HTTP library — network access
systematic-debugging/condition-based-waiting-example.ts · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.