ui-convert-ambiguity-resolver
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by processing arbitrary source code from the project environment.
- Ingestion points: Source code content from artifacts marked as 'unknown' is read from the file system (SKILL.md).
- Boundary markers: Absent; the instructions do not specify the use of delimiters to isolate untrusted code from agent instructions.
- Capability inventory: Read access to project source files and configuration; write access to 'index.json' and local log files. No network access or arbitrary command execution capabilities are present.
- Sanitization: Absent; the skill relies on the agent's reasoning to classify the provided code content.
Audit Metadata