extract
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code to identify patterns, which creates a surface for indirect prompt injection via malicious code comments or data.\n
- Ingestion points: Processes local files using search and directory analysis commands to identify extraction opportunities.\n
- Boundary markers: No explicit boundaries or instructions to disregard embedded content are provided for the agent when reading files.\n
- Capability inventory: The skill utilizes file search and file modification permissions to refactor and consolidate code components.\n
- Sanitization: No content validation or sanitization processes are implemented for ingested source code.
Audit Metadata