codex-test-gen
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes source code to generate unit tests, creating a surface for potential indirect prompt injection attacks from malicious content in target files.\n
- Ingestion points: The skill uses Read, Grep, and Glob tools to ingest file content.\n
- Boundary markers: There are no instructions or delimiters defined to mitigate embedded prompt risks in the processed code.\n
- Capability inventory: The skill has Write access to the filesystem and calls the mcp__codex__codex MCP tool.\n
- Sanitization: No sanitization or validation of target source code is specified.
Audit Metadata