ClawAudit verdict
meshcore-marketplace
AI agent marketplace client that uses MESHCORE_API_TOKEN to call documented meshcore.ai APIs; requires user confirmation before paid calls, behavior matches stated purpose.
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.
Findings (1)
Possible hardcoded credential
README.md ยท code ยท TOKEN="your-token-here
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: MESHCORE_API_TOKEN). Requires 2 system binaries. (1 elevated: curl).
network_outcredential_access Is this flag fair?
Thanks โ recorded.