Skills/ClawHub/skill-export-audit

skill-export-audit@1.2.2

VERIFIED· install only

Publisher claims: "Use before ClawHub export: audit skill, fix local + public." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher blueboyzx · publishing for 7 daysInstalls 271Last detonated 9 h ago
$clawhub install skill-export-audit
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 1.1.0

vet-skills diff skill-export-audit 1.1.0 1.2.2

In the sandbox, this version reached for nothing 1.1.0 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 2026-11-19 and scored it 88/100 (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

MEDIUM
File type combined with upload actionSKILL.md:91 · File type combined with upload action — agent may exfiltrate local data files…er's findings with `clawhub scan download <slug> --version <v>` (ZIP → `clawscan.json` per-dimension ratings/summary/guidance PLUS `skillspector.json` — the per-finding detail the dashboard renders: issueId, pattern name, severity, confide…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:54 · File type combined with upload action — agent may exfiltrate local data files…h> --no-input` (CR-normalize per Phase 6 step 2; exclude install metadata `_meta.json`/`.clawhub/` and the registry-generated `skill-card.md` from identity checks). The install is the only CLI path to the full published file tree — `clawhu…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈7,073 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.