Versioned security assessment

Report ID: SA-7AB40628

6/30/2026, 11:43:38 AM

rollinggo-searchhotel security assessment v2

Skill Security Certification Report

Audit History

Audit model: codex Historical report

Skill name: rollinggo-searchhotel
Version: v2
Maintainer: RollingGo-AI
Source: github.com/RollingGo-AI/rollinggo-skills/tree/main/rollinggo-hotel-cn/
Coverage: 4 Files scanned · 584 Lines analyzed
Policy version: Unavailable

Highest confirmed finding severity

Medium

2 confirmed security findings require attention.

Installation context

Historical evidence

This report may not describe the currently installable artifact. Open the current Skill page for install guidance.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

Static analysis correctly detected external command examples, API key handling, network references, and host environment configuration. Review found no prompt injection or confirmed malicious intent, but the skill should publish with a warning because it directs agents to run latest third-party CLI packages and handle RollingGo_API_KEY.

Report position

Historical report

Open audit history before using this report to install.

Audit attestation

Not attestable

The required immutable binding is incomplete.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

4 Files scanned · 584 Lines analyzed

2 items shown for review

Limitations

This report does not claim runtime or sandbox execution and does not prove the absence of side effects.

Evidence chain

Follow the evidence from source binding to the install contract. Available evidence supports verification; it is not a safety guarantee.

Source

Binding unavailable
Artifact

Identity incomplete
Audit

Complete
Install contract

Open manifest to verify
Open manifest

Capabilities observed

Observed means this report recorded supporting evidence. Not recorded does not prove that a capability is absent.

Contains scripts

May execute code included with the Skill.

Not recorded by this audit

Network access

May connect to external services.

Observed in 4 evidence locations

Filesystem access

May read or write local files.

Observed in 1 evidence location

Env variables

May read values from the process environment.

Observed in 5 evidence locations

External commands

May invoke commands or programs outside the Skill.

Observed in 3 evidence locations

Risk findings

Confirmed security concerns are separated from items that still need review.

Confirmed security concerns (2)

RISK-001 Medium

SKILL.md:57-63 references/rollinggo-npx.md:22-30 references/rollinggo-uv.md:25-37

Runtime Execution of Latest Third-Party CLI Packages

The skill instructs agents to execute rollinggo@latest through npx or uvx. This is legitimate for the hotel workflow, but it creates supply-chain risk because the package resolved at runtime can change after review.

The command execution instructions are explicit and semantically required by the skill. The risk is supply-chain exposure from latest package resolution, not evidence of malicious code in the skill files.

RISK-002 Medium

SKILL.md:10-13 SKILL.md:45 references/rollinggo-npx.md:69-79 references/rollinggo-uv.md:70-80

API Key Handling Through Environment and CLI Arguments

The skill requires RollingGo_API_KEY and documents passing it through environment variables or the --api-key option. This is expected for an authenticated API, but secrets can leak through shell history, logs, inherited environments, or host configuration if handled carelessly.

The files clearly require and document a real API key. The context is legitimate service authentication, but the exposure paths are common operational risks.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit: Unavailable
Content hash: Unavailable
Tree hash: Unavailable
Skill path: Unavailable
Audit payload hash: Unavailable

Analysis metadata

Audit model: codex

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Static false positives ignored (2)

Low

references/claw-host-env.md:31-32

Host Environment File Guidance Is Configuration Documentation

The scanner flagged hidden file access because the reference mentions .env paths and OpenClaw host configuration. The file only documents where users may store a key; it does not contain code that reads arbitrary files.

The relevant lines are documentation text about host configuration paths. No executable file-read logic or exfiltration path is present in the reviewed skill files.

Low

SKILL.md:1 references/claw-host-env.md:1 references/rollinggo-npx.md:1 references/rollinggo-uv.md:1

High Entropy Heuristic Appears to Be Natural Language Content

The scanner reported high entropy on the Markdown files. Review found normal Chinese and English documentation with command examples, not encoded payloads, binaries, encrypted blobs, or obfuscated scripts.

Manual review found Markdown documentation and examples only. No evidence of encoded content or hidden executable payloads was found.

Verify and export

JSON report CITATION.cff SARIF 2.1.0 Signed installation manifest

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: not_attestable