finalrun-generate-test
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
finalrun checkCLI tool to validate generated configurations and test suites. While this is the intended behavior for the tool's purpose, executing local binaries based on generated content is a capability that should be monitored. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the local repository to perform its tasks.
- Ingestion points: The agent is instructed to read application source code and existing configuration files in Step 1 and Step 1A to infer test logic and app identifiers.
- Boundary markers: The instructions do not provide specific delimiters or 'ignore' directives to prevent the agent from following instructions potentially embedded in code comments or strings within the files being read.
- Capability inventory: The skill allows for reading repository files, creating/updating YAML files, and executing the
finalrunCLI tool. - Sanitization: Output is restricted to strict, predefined YAML templates for tests and suites, which reduces the likelihood of the agent generating malicious executable scripts, though the content within the YAML strings remains a surface.
Audit Metadata