skills/tencentcloudbase/awesome-cloudbase-examples/cloudbase-document-database-web-sdk/Gen Agent Trust Hub
cloudbase-document-database-web-sdk
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- Prompt Injection (HIGH): High risk of Indirect Prompt Injection (Category 8) due to the combination of external data ingestion and write capabilities. \n
- Ingestion points: Untrusted data is retrieved via
db.collection().get()andwatcher.onChange()as shown inSKILL.md,pagination.md, andrealtime.md. \n - Boundary markers: Absent. There are no instructions or examples demonstrating the use of delimiters (e.g., XML tags or triple quotes) to isolate data from the agent's instructions. \n
- Capability inventory: The skill enables high-impact side-effecting operations including
add(),update(), anddelete(). \n - Sanitization: Absent. No logic for validating, escaping, or filtering database content is provided. \n- External Downloads (MEDIUM): The skill relies on the
@cloudbase/js-sdkNode.js package. While this is a standard library for Tencent CloudBase, it is an external dependency from a source that is not listed in the trusted scope, necessitating verification. \n- Command Execution (LOW): The skill documents the use of database methods that modify external state. While intended, this increases the potential impact of a prompt injection attack.
Recommendations
- AI detected serious security threats
Audit Metadata