Caveat verdict
design-panel
Accesses agent memory/notes AND makes external network calls
Multi-persona UX review skill that runs local analysis on a live app and writes report artifacts; telemetry is gated on user opt-in and all actions are transparent and consistent with the stated design review purpose.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses agent memory/notes AND makes external network calls — may leak personal data
LLM02 · LLM07 · ASI03 · ASI06
Accesses credentials AND writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Accesses agent memory AND writes files — may modify agent behavior persistently
LLM01 · LLM06 · ASI01 · ASI06
Accesses agent memory AND makes external network calls — may leak conversation history
LLM02 · LLM07 · ASI06
Permission integrity
network_out
file_read+write
agent_memory
Findings (1)
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class F). 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.
file_writeagent_memorynetwork_outnetwork_incredential_access Thanks — recorded.