backend-testing
Pass
Audited by Gen Agent Trust Hub on May 29, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill involves managing sensitive data such as authentication tokens, cookies, and database connection strings. It explicitly promotes security best practices by instructing the agent to use environment variables (
--connection-string-env) rather than passing credentials in plain text, which prevents sensitive information from entering the agent's context or history. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from potentially untrusted external sources, including API responses, server logs, and database records.
- Ingestion points: Untrusted data enters the agent context via the output of
request,log read, anddb querycommands in theSKILL.mdfile. - Boundary markers: The skill does not explicitly define delimiters or warnings to ignore instructions embedded in the verified data.
- Capability inventory: The agent has access to powerful capabilities through the
ironbee-backend-devtools-cli, including network requests, log monitoring, and database write operations. - Sanitization: No explicit sanitization or validation of the external content is documented within the skill's instructions.
Audit Metadata