ai-industrial-brutalist-ui
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface as it is designed to ingest and process data from untrusted external sources.
- Ingestion points: The skill accepts data through
materialUrl,materialFile, andmaterialTextparameters as defined inreferences/form-schema.jsonandreferences/skill.json. - Capability inventory: The included
scripts/run.pyscript enables network communication with theai-skills.aiplatform to process this data. - Boundary markers: The skill instructions do not implement delimiters or specific warnings to the agent to disregard instructions contained within the processed external content.
- Sanitization: No input validation or sanitization routines are present in the provided scripts to filter potentially malicious instructions from the ingested data.
- [EXTERNAL_DOWNLOADS]: The Python execution script references the
certifilibrary to handle SSL certificate verification for secure API requests. - Evidence:
import certifistatement inscripts/run.py. - [COMMAND_EXECUTION]: The skill includes a local Python script intended to be executed to facilitate communication with the backend API.
- Evidence: Instructions in
SKILL.mddirect the user to executepython3 scripts/run.py --params '...'to perform the visual diagnosis.
Audit Metadata