tencentcloud-cls
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill depends on the official
tencentcloud-sdk-pythonlibrary to interact with Tencent Cloud APIs. - [INDIRECT_PROMPT_INJECTION]: The skill ingests log data from external sources, which constitutes an attack surface for indirect prompt injection.
- Ingestion points: Log data retrieved through
client.SearchLogandDescribeTopicscalls withinSKILL.mdandscripts/cls.py. - Boundary markers: No explicit delimiters or instructions are present to prevent the agent from interpreting log content as commands.
- Capability inventory: The skill provides read-only access to log data; it does not contain functionality for file writing, code execution, or outbound network calls beyond the official API.
- Sanitization: Log content is decoded from JSON format but undergoes no secondary sanitization for malicious instruction patterns.
Audit Metadata