testing
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands through Bun (
bun run test,bun run test:coverage) to validate code quality and coverage. This behavior is standard and necessary for a development-focused skill. - [INDIRECT_PROMPT_INJECTION]: The workflow involves the agent reading and interpreting external data from test outputs and coverage reports, which represents a potential surface for indirect prompt injection.
- Ingestion points: The agent reads stdout and stderr from the
bun run testcommands executed in the shell. - Boundary markers: No specific delimiters or safety instructions are defined for the interpolation of test results into the agent's context.
- Capability inventory: The agent possesses the capability to execute shell commands and modify the filesystem based on these instructions.
- Sanitization: The skill does not describe any sanitization or validation of the test outputs before the agent processes them to determine the success of a task.
Audit Metadata