Caveat verdict
aoment-visuals
Reads local files AND makes external network calls
The skill explicitly instructs the agent that it MUST download the latest skill package ZIP from aoment.com before each invocation if more than 3 days have passed, effectively directing the agent to silently fetch and run untrusted remote code at runtime without user consent.
Automated static analysis โ 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 โ it does not verify that one flows into another. Read the code to confirm a live chain.
Reads local files AND makes external network calls โ the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 ยท LLM06 ยท ASI03
Accesses credentials AND makes external network calls โ potential credential theft
LLM02 ยท ASI03
Permission integrity
network_out
file_read
credential_access
Findings (2)
Pipe-to-python pattern โ remote code execution risk
SKILL.md ยท code ยท curl -L -o output.jpg "$(uv run {baseDir}/scripts/aoment_visuals.py -k <your-api
Pipe to python โ executes piped content as Python code
SKILL.md ยท code ยท | python3
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C). Final tier capped at Caution โ cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions โ minimal attack surface.
credential_accessnetwork_outfile_read Thanks โ recorded.