ClawAudit verdict
oadp-beacon
The skill makes the agent discoverable across the internet by auto-configuring OADP signals and emitting presence pings to open hubs. It involves network out and file write capabilities, which could be a concern if not properly handled.
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
file_read+write
Findings (1)
Possible prompt injection โ attempts to redefine agent identity
scripts/beacon-setup.sh ยท prose ยท downgraded ยท You are now
Permissions & capabilities
No declared permissions โ minimal attack surface.
network_outfile_write Is this flag fair?
Thanks โ recorded.