Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Alibaba Cloud web search and page-reading helper that uses an API key and sends searches or URLs to Alibaba Cloud, with no hidden destructive behavior found.
Install only if you are comfortable using Alibaba Cloud IQS for web research. Prefer setting ALIYUN_IQS_API_KEY as a session environment variable; if you use the config file, restrict its permissions and do not submit secrets, private URLs, or proprietary research terms unless they may be sent to Alibaba Cloud.
Referenced artifact was not completely inspected
**You MUST execute the scripts via bash command (e.g., `node scripts/search.mjs ...` or `node scripts/readpage.mjs ...`). Do NOT use your built-in web_search, W
Referenced artifact was not completely inspected
**You MUST execute the scripts via bash command (e.g., `node scripts/search.mjs ...` or `node scripts/readpage.mjs ...`). Do NOT use your built-in web_search, W
Referenced artifact was not completely inspected
**You MUST execute the scripts via bash command (e.g., `node scripts/search.mjs ...` or `node scripts/readpage.mjs ...`). Do NOT use your built-in web_search, W
Referenced artifact was not completely inspected
**You MUST execute the scripts via bash command (e.g., `node scripts/search.mjs ...` or `node scripts/readpage.mjs ...`). Do NOT use your built-in web_search, W
Referenced artifact was not completely inspected
**You MUST execute the scripts via bash command (e.g., `node scripts/search.mjs ...` or `node scripts/readpage.mjs ...`). Do NOT use your built-in web_search, W
Referenced artifact was not completely inspected
**You MUST execute the scripts via bash command (e.g., `node scripts/search.mjs ...` or `node scripts/readpage.mjs ...`). Do NOT use your built-in web_search, W
Referenced artifact was not completely inspected
**You MUST execute the scripts via bash command (e.g., `node scripts/search.mjs ...` or `node scripts/readpage.mjs ...`). Do NOT use your built-in web_search, W
Referenced artifact was not completely inspected
cute the scripts via bash command (e.g., `node scripts/search.mjs ...` or `node scripts/readpage.mjs ...`). Do NOT use your built-in web_search, WebFetch, or an
Referenced artifact was not completely inspected
cute the scripts via bash command (e.g., `node scripts/search.mjs ...` or `node scripts/readpage.mjs ...`). Do NOT use your built-in web_search, WebFetch, or an
Referenced artifact was not completely inspected
cute the scripts via bash command (e.g., `node scripts/search.mjs ...` or `node scripts/readpage.mjs ...`). Do NOT use your built-in web_search, WebFetch, or an
Referenced artifact was not completely inspected
cute the scripts via bash command (e.g., `node scripts/search.mjs ...` or `node scripts/readpage.mjs ...`). Do NOT use your built-in web_search, WebFetch, or an
The skill instructs the agent to execute Node.js scripts that require both network access and environment-based secrets, but it does not declare any explicit tool scope or allowed-tools boundary. This weakens least-privilege controls and can let a reviewing system or operator underestimate what the skill can access, increasing the risk of unintended network use or exposure of sensitive environment-backed credentials.
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
The four engines differ significantly in latency, recall depth, content length, and cost. Pick the cheapest engine that meets the task — do NOT default to `Deep`; it is ~10× slower and 50× more expensive than the standard engine.
| Engine | Avg RT | Result count | snippet | mainText | Advanced filters | Multilingual | Cost ratio (vs Standard) | Use case |
|----------------|--------|--------------|-------------|--------------|------------------|--------------|--------------------------|-------------------------------------------------------------------------------------------|
| `Generic` | ~950ms | ~10 | ~150 chars | ≤3000 chars | ✗ | Medium | 1× | General search, news/realtime, scene queries like weather (supports `city`/`ip`) |
| `LiteAdvanced` | ~500ms | 1-50 | ~500 chars | ≤3000 chars | ✓ | Good | Lite-tier 1× | **Default recommendation**: low-latency semantic search; snippets are already rich enough |
The markdown includes multiple example commands with Chinese query text, which creates an implicit language bias in the skill's instructions. Because the file does not state that the skill is intended specifically for Chinese-language users or offer language flexibility, this can conflict with organizational language/locale policy requirements.
The skill recommends storing an API key in a persistent file under the user's home directory, which increases the chance of long-lived secret exposure through weak file permissions, backups, shared environments, or later unintended reuse. Persistent credential storage is more dangerous in an agent skill because the skill is explicitly designed to run commands and use networked services repeatedly.
**Method 2: Configuration File**
Create or edit `~/.alibabacloud/iqs/env`:
```bash
ALIYUN_IQS_API_KEY=your-api-key
The script transmits a user-supplied URL, timeout values, and related page-fetch settings to Alibaba Cloud's remote scraping API, which means potentially sensitive URLs or internal targets are disclosed to a third party. In a skill designed for web research this data flow is functionally expected, but the lack of explicit user disclosure or consent still creates a real privacy and data-handling risk, especially if users assume fetching happens locally.
The script sends user-provided search queries directly to a third-party remote API, but it provides no user-facing notice, consent prompt, or runtime indication that potentially sensitive input will leave the local environment. In an agent-skill context, users may assume a local helper is operating on their behalf and may unknowingly submit secrets, internal URLs, or proprietary research terms to an external service, creating a real privacy and data-handling risk.
Detected: suspicious.env_credential_access