Skills
skills/softaworks/agent-toolkit/qa-test-planner/Gen Agent Trust Hub

qa-test-planner

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (HIGH): Vulnerable shell scripting in scripts/create_bug_report.sh and scripts/generate_test_cases.sh. Both scripts use eval to assign user-provided input to variables. This is a direct command injection vector.
  • Evidence: The function prompt_input uses eval "$var_name=\"$input\"". An attacker providing input like "; touch /tmp/pwned; #" would result in the execution of the injected command.
  • [Indirect Prompt Injection] (LOW): The skill provides an attack surface for indirect prompt injection by ingesting untrusted data and interpolating it into prompts/files without sanitization.
  • Ingestion points: Interactive user prompts in create_bug_report.sh and generate_test_cases.sh.
  • Boundary markers: None used in generated markdown templates.
  • Capability inventory: Shell command execution via eval, file system write access.
  • Sanitization: No input validation or escaping is performed on the user-provided data before processing.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 04:34 PM