awk-img-gen

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Uses a shell wrapper (awk-img-gen.sh) to execute the core Python logic. The wrapper correctly handles path resolution for symbolic links and forwards all arguments to the Python interpreter without modification.
  • [EXTERNAL_DOWNLOADS]: Downloads generated image content from official Aliyun DashScope endpoints (aliyuncs.com). These network operations are necessary for the skill's purpose and target a well-known technology service.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text prompts and images, creating a potential surface for injection. 1. Ingestion points: The --prompt and --image CLI arguments in scripts/gen.py. 2. Boundary markers: User data is encapsulated within structured JSON payloads for API transmission. 3. Capability inventory: The script has the ability to read local files provided as arguments, perform network requests to Aliyun, and write generated images to local storage. 4. Sanitization: The skill employs standard JSON encoding for transmission and relies on the safety filters of the upstream service provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 04:50 PM