gbro-social-cover-generator
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches configuration, style templates, and few-shot examples from a GitHub repository (
pyang5166/gbro-cover-design) as part of the initial installation and setup process. - [PROMPT_INJECTION]: The skill ingests untrusted article content from the user to provide style recommendations and title suggestions, creating a potential surface for indirect prompt injection.
- Ingestion points: Round 1 of the interactive workflow (SKILL.md) where the agent analyzes provided article content.
- Boundary markers: Absent; the skill does not explicitly use delimiters or ignore-instructions for the processed article text.
- Capability inventory: The skill's primary capabilities are limited to generating production-ready text prompts for external image models; it does not perform automated network operations or file system modifications beyond local configuration.
- Sanitization: No sanitization or validation of the input article content was identified.
Audit Metadata