Skills/ClawHub/convo-vault

convo-vault@1.0.2

VERIFIED· install only

Publisher claims: "Export or archive ChatGPT, Grok and Gemini chats in local Markdown, PDF and JSONL. Preserve original languages and review available reasoning and tool records. Supports whole ChatGPT projects." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher violet-amethyst · publishing for 2 daysInstalls 109Last detonated 46 min ago
$clawhub install convo-vault
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 1.0.1

vet-skills diff convo-vault 1.0.1 1.0.2

In the sandbox, this version reached for nothing 1.0.1 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 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

HIGH
Authorization escalation languageSKILL.md:99 · Authorization escalation language1. Open the browser's extensions page (`chrome://extensions` or `edge://extensions`) and turn on **Developer mode**.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injectionSKILL.md:99 · Prompt injection — known jailbreak technique reference1. Open the browser's extensions page (`chrome://extensions` or `edge://extensions`) and turn on **Developer mode**.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actionSKILL.md:135 · File type combined with upload action — agent may exfiltrate local data files…s separate thinking panel is currently outside the capture. Check `*.agent-trace.json` for coverage. **Files** uploaded to or generated in the conversation are only downloaded on request. Ask the …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
≈3,789 tok
1 file · 1 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.