openscad

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Argument injection vulnerability in scripts/version-scad.sh. The ls command does not use the -- delimiter to separate options from arguments, allowing a model name starting with a hyphen to be interpreted as command-line flags.\n- [COMMAND_EXECUTION]: Path traversal risk in scripts/version-scad.sh. The script does not sanitize the MODEL_NAME argument, which allows it to contain path components or wildcards that could be used to probe for the existence of files or list directory contents outside of the intended scope.\n- [PROMPT_INJECTION]: Indirect prompt injection surface via tool output poisoning in scripts/version-scad.sh.\n
  • Ingestion points: User-controlled model name provided as an argument to the script.\n
  • Boundary markers: None present in the script or usage instructions.\n
  • Capability inventory: The skill allows the agent to execute Bash commands and write files, creating a risk if the agent uses a malicious filename generated by the script in a subsequent command.\n
  • Sanitization: No validation or escaping is performed on the input before it is used in shell commands or included in the script's output.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 05:42 AM