identify-dominant-frame
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown-formatted instructions and YAML metadata. It does not include or reference any Python scripts, Node.js packages, shell commands, or binary executables.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data fields which constitutes an attack surface.
- Ingestion points: Data provided via problem_statement, current_representation, and stakeholder_views in SKILL.md.
- Boundary markers: Absent. The prompt does not specify delimiters to isolate untrusted input.
- Capability inventory: None. The skill does not have access to any tools, network, or filesystem operations.
- Sanitization: Absent. There are no instructions for sanitizing or filtering input content.
Audit Metadata