test-smell-detection
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection Surface: As a code auditing tool, this skill is designed to ingest and process user-provided test files. This creates a standard surface for indirect prompt injection where instructions embedded within test code could potentially influence the agent's behavior. This is an inherent property of the skill's primary function and is mitigated by the agent's underlying safety protocols.
- Ingestion points: Test files or project directories provided by the user for analysis (identified in Step 2 of the workflow).
- Boundary markers: The skill does not explicitly define custom delimiters (e.g., XML-style tags) for the test code content within its instructions.
- Capability inventory: The skill utilizes file system read access and the ability to invoke the
test-analysis-extensionsskill. - Sanitization: No specific sanitization or filtering of the content within test files is described beyond standard pattern matching for smells.
Audit Metadata