tencentcloud-cos

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the official cos-python-sdk-v5 package, which is a well-known library for interacting with Tencent Cloud services.\n- [COMMAND_EXECUTION]: The skill executes a provided Python script (scripts/cos.py) to wrap cloud storage operations into a user-friendly CLI format.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes metadata and object keys retrieved from the Tencent Cloud API.\n
  • Ingestion points: Remote data such as bucket names and object keys are retrieved from the Tencent Cloud COS API through the list_buckets and list_objects methods.\n
  • Boundary markers: The skill does not use specific delimiters or instructions to isolate remote data from the agent's internal reasoning context.\n
  • Capability inventory: The skill includes capabilities to read and write files on the local filesystem and to perform authenticated network requests to Tencent Cloud domains.\n
  • Sanitization: The skill relies on the official SDK's standard data handling for cloud responses without additional content filtering or sanitization of object metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:12 PM