short-drama-image-prompts
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust validation framework in
scripts/image_prompt_check.py. This script specifically scans for and rejects input containing 'VENDOR_FIELDS' such as API keys, access tokens, and passwords, which is a proactive security measure to prevent credential leakage in production metadata. - [SAFE]: The skill uses a structured 'Stage Contract' (
references/stage-contract.md) and strict JSONL schemas to ensure data integrity and prevent logical errors in prompt generation. This reduces the risk of unintended behavior resulting from malformed project data. - [SAFE]: All provided scripts (
image_prompt_check.pyandselftest.py) use standard Python libraries and perform no network operations, privilege escalations, or dynamic code execution. They are restricted to file-system path validation and JSON parsing. - [SAFE]: The instructions explicitly state that the skill does not call external services or generate images directly, mitigating risks associated with remote execution or unauthorized API usage.
Audit Metadata