Caveat verdict
smart-charts
Installs packages AND executes processes
Generates charts from user data using sandboxed LLM transform code with keyword blacklist and AST whitelist; dynamic_eval is within a documented sandbox not remote execution.
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.
Installs packages AND executes processes — opaque dependency chain with execution
LLM03 · ASI04
Permission integrity
package_install
Findings (4)
<script> tag in markdown — potential code injection
core/chart_generator.py · prose · downgraded · <script
Uses eval() — can execute arbitrary code
core/data_transformer.py · prose · downgraded · eval(
Uses exec() — may execute shell commands
core/data_transformer.py · prose · downgraded · exec(
subprocess execution — runs system commands from Python
core/generate_hashes.py · prose · downgraded · subprocess.run(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D/G). 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.
package_installprocess_execdynamic_eval Thanks — recorded.