Security audit

Xiaohongshu Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Xiaohongshu content-analysis helper with purpose-aligned network and parsing dependencies, but users should be aware it may fetch public social-media pages and installs unpinned Python packages.

Install this only if you are comfortable with an agent fetching public Xiaohongshu pages for analysis and installing common Python scraping dependencies from pip. Use it on public content, confirm before analyzing account/profile URLs, and prefer a controlled Python environment with pinned dependencies if you need stricter supply-chain hygiene.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:13
Finding: Unpinned Third-Party Python Dependencies
Content: View full analysis
Remediation: View remediation
" ``` 2. Maintain a lock file that also constrains transitive dependencies to reviewed versions. 3. Record and enforce cryptographic hashes for every approved distribution artifact. For pip-based installation, use a hashed requirements file together with `pip install --require-hashes`. 4. Prefer reviewed binary wheels from an explicitly configured trusted package index, where practical, and avoid unexpected source builds. 5. Install dependencies inside an isolated virtual environment under a non-privileged account. 6. Use automated dependency scanning and a controlled update process so pinned versions still receive timely security updates. 7. Validate index configuration to prevent untrusted mirrors or additional package sources from taking precedence. ]]>

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill exposes very generic natural-language trigger examples such as asking to analyze a post, find keywords, or discover hot topics, without requiring an explicit skill invocation boundary. In an agent system that auto-matches skills from user intent, these broad phrases could cause unintended activation during ordinary conversation, leading the agent to fetch external URLs or perform scraping-oriented actions unexpectedly.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.