laravel-test

Warn

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to interpolate the $ARGUMENTS variable directly into shell commands, such as 'php artisan test --filter=$ARGUMENTS'. This creates a risk of command injection if the user-provided arguments contain shell metacharacters like semicolons, pipes, or ampersands.
  • [PROMPT_INJECTION]: The skill features an automated 'fix loop' that reads external data (test failure output and source code) and uses it to drive agent actions. This constitutes an indirect prompt injection surface where malicious code or test data could influence the agent's behavior during the repair process. Ingestion points: Reads test output and project source code via Read and Bash tools. Boundary markers: The instructions lack delimiters or warnings to ignore embedded instructions in the processed files. Capability inventory: Includes Bash for command execution and Edit for modifying the filesystem. Sanitization: No filtering or sanitization of the ingested content is specified before processing.
  • [SAFE]: The skill uses dynamic context injection syntax ('!') to gather environment data (artisan about, composer.json). These commands are benign informational checks and do not involve user-controlled arguments at load time.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 8, 2026, 11:24 AM