test-anti-patterns
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to ingest and analyze untrusted content from external source code files (test files and production code). This introduces a potential surface for indirect prompt injection where malicious instructions embedded in code comments or strings could attempt to influence the agent's analysis or behavior.
- Ingestion points: The skill gathers content by reading test and production files from the user's environment as described in the Workflow (Step 2).
- Boundary markers: There are no explicit instructions to use delimiters or specific warnings to ignore instructions that might be present within the analyzed code.
- Capability inventory: The skill's primary purpose is diagnostic; it does not request or demonstrate capabilities for network operations, file system modifications, or subprocess execution within its own instructions.
- Sanitization: The instructions do not describe a process for sanitizing or filtering input code before it is processed by the agent.
Audit Metadata