aws-wechat-sticker
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local Python scripts to handle specialized tasks. It executes
image_create.py(from the siblingaws-wechat-article-imagesskill) to generate images andpublish.py(fromaws-wechat-article-publish) to upload content to WeChat. - [CREDENTIALS_UNSAFE]: Accesses the
aws.envfile to retrieve sensitive credentials, includingIMAGE_MODEL_API_KEY,WECHAT_1_APPID, andWECHAT_1_APPSECRET. This is standard practice for the skill's automation workflow. - [DATA_EXFILTRATION]: Transmits the
IMAGE_MODEL_API_KEYto the endpoint specified in the user's configuration and uploads generated image files to the official WeChat API. These network operations are core to the skill's functionality. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external data to build prompts for image generation.
- Ingestion points: Reads metadata and instructions from
article.yaml,topic-card.md, and user-provided theme descriptions. - Boundary markers: None identified in the prompt construction logic.
- Capability inventory: Shell execution (
python3), network requests (image and WeChat APIs), and filesystem writes (imgs/directory). - Sanitization: No specific sanitization or filtering of input data is mentioned before it is used in prompt construction.
Audit Metadata