get-qiwei-message

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements its documented purpose of querying chat records from a specific API gateway without any hidden or suspicious behavior.
  • [CREDENTIALS_UNSAFE]: No hardcoded credentials or secrets were found. The skill correctly instructs the user to configure sensitive information such as QIWEI_OPEN_APP_KEY and QIWEI_OPEN_CORP_ID through environment variables.
  • [DATA_EXFILTRATION]: The skill accesses sensitive chat data, but this is its primary stated functionality. The data is sent to and retrieved from a specific corporate gateway (gateway.test.xdf.cn) and is not exfiltrated to unauthorized third-party domains.
  • [PROMPT_INJECTION]: The skill processes external chat data, creating a surface for indirect prompt injection.
  • Ingestion points: scripts/get_qiwei_message.py fetches chat message content from the remote WeCom API.
  • Boundary markers: None present; the script returns raw JSON data from the API response to the agent context.
  • Capability inventory: The skill has the ability to perform network POST requests and read local JSON files.
  • Sanitization: No sanitization or filtering of the retrieved chat message content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 08:35 AM