Caveat verdict
AI Rankings Leaderboard
ai-leaderboard
Receives external input AND uses eval
This skill queries AI model rankings from documented public sources (OpenRouter, Artificial Analysis, Pinchbench) via a browser dependency — behavior is fully consistent with its stated leaderboard querying 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.
Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)
LLM01 · LLM05 · ASI01 · ASI05
Permission integrity
package_install
Findings (2)
subprocess execution — runs system commands from Python
fetch_rankings.py · prose · downgraded · subprocess.run(
Python urllib.request — network access
query_leaderboard.py · prose · downgraded · urllib.request
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.
package_installnetwork_indynamic_eval Thanks — recorded.