Skills/ClawHub/drakon-agent-optimizer

drakon-agent-optimizer@0.16.4

VERIFIED· install only

Publisher claims: "CLI tool that audits Claude Code, OpenClaw, and Hermes Agent config files for misconfigurations, token waste, security issues, and stale auth. Audit, scan, and optimize make no network calls. No API keys required. Network use is command-triggered: license activation (including reactivation), update queries to the configured npm registry and a global npm install if versions differ, optional monitor enroll/run/disable POSTs, buy opening the purchase page in your browser, and fleet SSH reads — see Data & Network Disclosure." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher jarvis-drakon · publishing for 34 daysInstalls 1,867Last detonated 34 min ago
$clawhub install drakon-agent-optimizer
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 0.16.3

vet-skills diff drakon-agent-optimizer 0.16.3 0.16.4

In the sandbox, this version reached for nothing 0.16.3 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-21 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsSKILL.md:41 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFleet SSH audit uses the user's existing SSH config (~/.ssh/config) andFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionSKILL.md:92 · File type combined with upload action — agent may exfiltrate local data files- `~/.openclaw/agents/*/agent/auth-profiles.json` — token expiry and duplicate-key checks (does NOT transmit keys)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsSKILL.md:108 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…at ~/.openclaw/openclaw.json` over SSH on each listed host using your existing `~/.ssh/config` entries. It does not store, copy, or prompt for SSH keys. Requires Flee…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Unpinned dependencySKILL.md:130 · Unpinned dependency(`npm install -g @drakon-systems/agent-optimizer@latest`).Fix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06

Cost to the agent

Instructions loaded
≈4,042 tok
1 file · 2 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.