extract
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to analyze local source code and design files to identify patterns for extraction. This creates a surface for indirect prompt injection if the files being analyzed contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads local project files, component directories, and styling files (SKILL.md).
- Boundary markers: The instructions do not define explicit delimiters or warnings to treat ingested code content as data only.
- Capability inventory: The skill involves file analysis (reading), component creation (writing), and migration (refactoring/deleting code).
- Sanitization: No sanitization or validation of the ingested code content is specified before the agent performs refactoring tasks.
Audit Metadata