codeguard-cobol
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes COBOL source files (.cbl, .cob, .cpy), which serves as an ingestion surface for potentially malicious data that could influence the agent's behavior.\n
- Ingestion points: COBOL source and copybook files identified in the tooling configuration.\n
- Boundary markers: No specific delimiters or safety warnings are defined to isolate untrusted code from instructions.\n
- Capability inventory: The skill is designed to call local diagnostic tools, creating an execution vector for data-driven attacks.\n
- Sanitization: There is no mention of sanitizing or escaping the content of processed files.
Audit Metadata