finding-tests

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill constructs and executes shell-like commands via execute_tool using the findTests utility. It performs string interpolation of user-supplied values—including class names, namespaces, and absolute file paths—directly into the command arguments. This pattern is susceptible to command injection if the input contains shell metacharacters (such as backticks, semicolons, or pipes) that are not properly sanitized or escaped before execution.
  • [PROMPT_INJECTION]: The skill processes untrusted data from user requests to perform its primary function.
  • Ingestion points: Class names, namespaces, and file paths supplied by the user as arguments for the findTests command.
  • Boundary markers: The instructions recommend quoting values with spaces but do not provide comprehensive delimiters or instructions to the agent to ignore embedded instructions within the data.
  • Capability inventory: The skill uses execute_tool to run external commands.
  • Sanitization: No explicit sanitization, validation, or escaping of shell-sensitive characters is implemented beyond basic quoting recommendations for spaces.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 06:26 PM
Security Audit — agent-trust-hub — finding-tests