ClawAudit verdict
agent-task-marketplace
mirageclaw-marketplace
The skill interacts with the Mirage marketplace API, which could potentially be used for malicious purposes.
⚠ 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 (5)
References child_process — can spawn system processes
scripts/approve.js · prose · downgraded · child_process
Uses spawn() — can execute external programs
scripts/listen.js · prose · downgraded · spawn(
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Uses XMLHttpRequest — network access
package-lock.json · prose · downgraded · xmlhttprequest
Accesses sensitive environment variables
scripts/bid.js · prose · downgraded · process.env.MARKETPLACE_API_KEY
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
Requires 1 environment variable. (1 sensitive: MARKETPLACE_API_KEY). Requires 4 system binaries. (1 elevated: curl).
network_incredential_access Is this flag fair?
Thanks — recorded.