ios-design-workflow
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (CRITICAL): Automated scanning (URLite) detected a blacklisted malicious URL in the skill component 'requirements.md'. This represents a confirmed detection of a malicious resource link within the skill package.
- [COMMAND_EXECUTION] (SAFE): The skill utilizes GitHub CLI and Gitea MCP to manage project issues and documentation. These commands are typical for the stated purpose of an iOS design workflow and do not exhibit signs of malicious command injection or privilege escalation.
- [PROMPT_INJECTION] (LOW): The skill exhibits a surface for indirect prompt injection (Category 8) as it processes untrusted user-provided app ideas and forwards them to external tools. Mandatory Evidence: 1. Ingestion points: Phase 1 brainstorming dialogue (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: File writing to 'docs/' and issue creation via GitHub CLI/Gitea MCP. 4. Sanitization: Absent.
Recommendations
- AI detected serious security threats
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata