gbro-cover-design
Warn
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The installation instructions require the user to clone a repository from
https://github.com/pyang5166/gbro-cover-design.git. This repository is hosted by an unverified third-party account rather than a trusted organization, making the downloaded templates and logic unverifiable.- [INDIRECT_PROMPT_INJECTION]: The skill ingests article content to automatically recommend design styles and generate titles, creating an attack surface for embedded instructions. - Ingestion points: User-provided article content passed during the first round of the workflow in
SKILL.md. - Boundary markers: Absent; the skill does not use delimiters or instructions to ignore embedded commands within the ingested article content.
- Capability inventory: The skill performs prompt generation and user interaction within the agent environment; no high-risk command execution or network exfiltration capabilities were detected.
- Sanitization: No sanitization, filtering, or validation steps are documented for the external article content before processing.
Audit Metadata