Back to skill

Security audit

Xiaohongshu CN

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a Xiaohongshu research guide, but it tells users to clone, install, and run mutable third-party scraper code without pinning or integrity checks.

Review the external scraper before running it, pin it to a trusted commit, use a fresh virtual environment or container, avoid exposing browser profiles or credentials, and confirm that any scraping or packet capture complies with Xiaohongshu rules and applicable privacy obligations.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Warning
Location
SKILL.md:24
Finding

Execution of Mutable Third-Party Code and Unpinned Dependencies

Content
View full analysis
Remediation
View remediation
``` 2. Verify the checked-out commit against a documented expected SHA and, where available, verify a signed release or signed commit. 3. Audit and lock all Python dependencies to exact versions. Use a hash-locked requirements file and enforce verification: ```bash python -m pip install --require-hashes -r requirements.lock ``` 4. Host the reviewed lockfile within the Skill package or provide its expected cryptographic digest so changes to upstream dependency declarations cannot silently alter installation behavior. 5. Review package build configurations and installation hooks before installation. Avoid dependencies sourced from mutable Git branches, arbitrary URLs, or untrusted package indexes. 6. Run the scraper inside an isolated, least-privilege environment such as a disposable container or virtual machine. Do not mount credential directories or unrelated host data, and restrict outbound network access to required destinations. 7. Use a dedicated non-administrative account and a fresh virtual environment. Do not expose API keys, browser profiles, SSH keys, cloud credentials, or sensitive environment variables to the process. 8. Document the exact reviewed repository revision, dependency set, verification procedure, and update-review process in `SKILL.md`. ]]>
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README explicitly recommends scraping or third-party tooling for a platform that does not provide a public API, but gives no warning about legal, terms-of-service, account suspension, privacy, or data-handling risks. In a skill intended for Xiaohongshu analysis, this omission can normalize unsafe collection practices and lead users to deploy scraping workflows without understanding the compliance and security implications of credential use, proxying, or untrusted third-party code.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

Natural-language policy violations include forcing a specific language without user opt-in. The title and description are entirely in Chinese, and the README does not indicate that the skill is region-specific or offer any alternative language option.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file’s title and description are entirely in Chinese and present the skill as a China-specific analysis tool without stating that language is optional or user-selectable. Under the policy, forcing a specific language or locale without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description is written entirely in Chinese and presents the skill as China-specific analysis, but the file provides no indication that users can choose another language or that the locale restriction is explicitly justified. This can violate language/locale policy when a skill appears to assume a specific language by default.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.