test-bruno
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to review and write .bru files, creating a surface where malicious instructions embedded in those files could influence agent behavior.\n
- Ingestion points: The agent is tasked with reviewing .bru request files and environment configurations (SKILL.md, references/collections.md).\n
- Boundary markers: There are no instructions provided to delimit or wrap the content of .bru files to prevent the agent from interpreting data as instructions.\n
- Capability inventory: The agent's core task involves analyzing and generating code-like content for API tests (SKILL.md).\n
- Sanitization: No sanitization or validation steps are defined for the content processed from .bru files.\n- [DYNAMIC_EXECUTION]: The skill provides static templates for generating scripting blocks that are executed by the Bruno runtime.\n
- Evidence: The skill includes examples of pre-request and post-response Javascript scripts in references/scripting-and-assertions.md.\n
- Context: These are standard templates for the Bruno tool and represent a low-risk use of script generation from known patterns.
Audit Metadata