Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed QVeris connector that sends selected tool queries and parameters to qveris.ai using the user's API key, with no hidden local persistence or destructive behavior found.
Install this only if you are comfortable giving the skill a QVeris API key and sending capability queries plus selected tool parameters to QVeris. Avoid using it for sensitive personal, credential, or confidential business data unless that external transmission is intended.
The skill declares outbound network access to qveris.ai and describes multiple invocation paths, but it does not constrain tool scope via explicit permissions or allowed-tools. In agent environments, that omission can let the skill trigger broader tool usage than intended, increasing the chance of unauthorized external calls or fallback to riskier execution paths.
The description mandates English discovery queries, overriding user language preference without consent. While not a classic code-execution issue, it is a policy and safety concern because it can cause unintended transformation of user input before external transmission and degrade correctness for multilingual users.
The instructions require converting all non-English user requests into English capability queries before using the external service. This creates a language-policy and data-handling risk because user inputs are systematically transformed and then sent off-platform, which can alter meaning, reduce fidelity, and transmit content in a form the user did not request.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
| Wrong date format | `"date": "01/15/2026"` | `"date": "2026-01-15"` (ISO 8601) |
| Missing required param | Omitting `symbol` for a stock API | Always check required list |
| Natural language or wrong format as param | `"query": "what is AAPL price"` or `"symbol": "Apple"` | Extract structured values: `"symbol": "AAPL"` |
| Constructing API URLs manually | Directly calling `https://api.qveris.com/...` | Use the API reference above or the script |
| Giving up after one failure | "I don't have real-time data" / abandoning after error | Discover first; follow Error Recovery on failure |
| Not trying http_request when exec fails | Abandoning when node/exec is unavailable | Use http_request tool (Tier 2) — it works without exec |
No suspicious patterns detected.