test-audit
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content including test files, production source code, and project-specific configuration files. Maliciously crafted instructions within these files could influence the agent's behavior or decisions during the audit process.
- Ingestion points: Reads repository files such as AGENTS.md, test suites, production code, and dependency files.
- Boundary markers: No explicit markers or instructions to ignore potential commands embedded within the analyzed data were found.
- Capability inventory: The skill performs file reads, file writes (mutations), and executes shell commands (test runners and project-specific executables).
- Sanitization: The skill lacks explicit sanitization or validation of the content ingested from the repository before using it to guide its logic.
- [COMMAND_EXECUTION]: The skill is instructed to execute local test runners and project binaries to validate changes. This capability allows the agent to run arbitrary scripts or executables found within the repository context.
Audit Metadata