project-brief-designer
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were found in the skill definition.
- [SAFE]: The skill ingests untrusted user input (e.g., project topics and student profiles) without explicit delimiters. This constitutes an indirect prompt injection surface. However, the risk is negligible as the skill lacks tool-calling capabilities, network access, or file system permissions. Ingestion points: project_topic, learning_objectives, student_profiles in SKILL.md. Boundary markers: Absent. Capability inventory: Purely generative; no shell, file system, or network tools are permitted. Sanitization: None.
Audit Metadata