running-chaos-tests
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool with a prefix restriction of 'test:chaos-*'. This allows the agent to execute specific chaos engineering binaries and associated local scripts, such as 'inject_failure.py' and 'validate_resilience.py', which is necessary for its primary function of testing system resilience.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of external data during the testing and reporting process.
- Ingestion points: The skill reads configuration files from the '{baseDir}/config/' directory and parses execution outputs from chaos testing tools to generate reports.
- Boundary markers: No specific delimiters or instructions to ignore embedded instructions are used when reading configuration or test output data.
- Capability inventory: The skill has access to file system operations (Read, Write, Edit) and command execution via the Bash tool.
- Sanitization: There is no evidence of input validation, sanitization, or escaping of the ingested data before it is processed or included in findings.
Audit Metadata