bruno-new-endpoint
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process external API documentation from the web, which creates a surface for indirect prompt injection attacks.
- Ingestion points: Step 1 uses
WebFetchorcontext7to retrieve documentation from external URLs. - Boundary markers: The instructions do not specify delimiters or provide warnings for the agent to ignore instructions embedded within the fetched content.
- Capability inventory: The skill has both read access (Step 2: reading existing
.brufiles) and write access (Step 4: invoking/brunoto create files). - Sanitization: There is no requirement for the agent to validate or sanitize the fetched documentation before processing it.
- [DATA_EXFILTRATION]: The skill requires the agent to read existing
.brufiles in the project to understand naming and authentication conventions. Since Bruno files frequently contain sensitive information such as API keys, authentication tokens, and environment variables, this access constitutes a risk of data exposure if the agent's behavior is influenced by malicious external documentation.
Audit Metadata