expand-the-frame
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains purely instructional content focused on critical thinking and project analysis, with no executable malicious code identified.
- [SAFE]: No sensitive data access, hardcoded credentials, or unauthorized network operations were detected in the files.
- [SAFE]: No obfuscation techniques, such as Base64, zero-width characters, or homoglyphs, were found.
- [SAFE]: The skill references other platform-standard skills ('simple-english' and 'investigate-with-evidence') for specialized tasks like factual verification and prose formatting, which follows standard modular design practices.
- [INDIRECT_PROMPT_INJECTION]: The skill ingest project materials and user input to drive the discussion, creating a theoretical attack surface. However, the instructions explicitly prioritize evidence-based reasoning and separate hypothetical scenarios from verified facts, providing conceptual mitigation. Following security guidelines, this is categorized as safe given the primary purpose of the skill.
Audit Metadata