Caveat verdict
aiusd-skill
aiusd-skill-agent
This skill contains extensive instructions that hijack agent output behavior — prohibiting specific words, banning disclosure of the auth login URL to users, and dictating agent response phrasing — which is a form of prompt injection that manipulates agent transparency toward users.
⚠ 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.
Permission integrity
network_out
Findings (3)
Recursive delete from root or home — destructive command
SKILL.md · prose · downgraded · rm -rf ~
References child_process — can spawn system processes
aiusd-skill-installer.js · prose · downgraded · child_process
Long base64 string (100+ chars) — likely obfuscated payload
aiusd-skill-installer.js · prose · downgraded · H4sIAGHei2kAA+y923IjSZYg1rtmsjVBz9KzFytnALCAIADeMpGXaiaT2cVuJplNMqu2lJlDBoEgEZUA
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.
network_out Is this flag fair?
Thanks — recorded.