Skills/ClawHub/sglang-amd-bench

sglang-amd-bench@0.1.0

CAUTION· static only

Publisher claims: "Benchmark sglang serving performance on AMD Instinct GPUs (MI355X, MI300X, MI308X) with various parallel configurations (TP, DP, EP). Covers throughput/laten..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher alexsun07 · publishing for 199 daysInstalls 732Last detonated 27 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-22 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
File type combined with upload actionSKILL.md:509 · File type combined with upload action — agent may exfiltrate local data files…─ ... ``` Each config gets its own directory. `serve.sh` writes `server_<LABEL>.log` into `LOG_DIR`. `bench.sh` writes JSONL into `OUTPUT_DIR`; capture its stdout/stderr to the same `OUTPUT_DIR` via `2>&1 | tee $OUTPUT_DIR/<bench>.log`. Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandscripts/stop.sh:3 · Process kill command — agent can terminate processes# Stop sglang server (kill matching processes inside this container).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/stop.sh:13 · Process kill command — agent can terminate processesps -ef | grep -i sglang | grep -v grep | awk '{print $2}' | xargs -r kill -9Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:70 · Process kill command — agent can terminate processes- Between configs, fully kill the sglang server and wait for GPU memory to be freed before relaunching.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈6,469 tok
1 file · 10 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim alexsun07: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim alexsun07Propose a patch to the maintainer