fix-flaky-tests
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
tuistandxcodebuildCLI tools to retrieve test metrics, list flaky runs, and verify fixes. These commands are executed with parameters such as test case IDs, identifiers, and iteration counts derived from test logs or user input. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests and processes untrusted data from the project environment.
- Ingestion points: Failure messages, crash reports, and source code files identified in
failures[].path(referenced inSKILL.md). - Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions that might be embedded within test logs or source code.
- Capability inventory: The skill allows the agent to execute shell commands and modify project source code across all scripts.
- Sanitization: There is no evidence of sanitization or validation of the log content before it is processed by the agent.
Audit Metadata