test-gap-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill is designed to discover and run test commands from project manifests, such as
dotnet runfor .NET projects. This is a standard requirement for empirical test verification, though it involves executing commands determined by the project's configuration files. - Indirect Prompt Injection: The skill's workflow involves ingesting and analyzing untrusted production and test code. This represents a potential surface for indirect prompt injection, where instructions embedded in the analyzed code could attempt to influence the agent's behavior during the mutation or verification process.
- Ingestion points: Production source code, test suites, and project manifests (SKILL.md, Step 1 & 3).
- Boundary markers: Not explicitly defined for ingested code content.
- Capability inventory: Execution of shell commands (e.g.,
dotnet run) and file modification for mutation testing (SKILL.md, Step 2 & 6). - Sanitization: No explicit sanitization of ingested code content is mentioned.
- Dynamic File Modification: As part of its verification process, the skill temporarily modifies source code by applying 'mutations' (e.g., changing logic or constants). The skill includes safeguards to revert these changes immediately, but the capability to edit production files is an inherent part of mutation testing.
Audit Metadata