image-crop-rotate

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (HIGH): The skill instructions direct the agent to execute a shell command python scripts/crop_and_rotate.py <input_path> <output_path> where the paths are derived from user-uploaded files. This pattern is highly susceptible to command injection if a user uploads a file with a name containing shell metacharacters like semicolons or backticks.
  • [PROMPT_INJECTION] (HIGH): The skill exhibits a significant indirect injection surface. Evidence: 1. Ingestion points: File paths for images in /mnt/user-data/uploads/. 2. Boundary markers: Absent; there are no instructions to delimit or escape the paths. 3. Capability inventory: Execution of a Python subprocess via the shell. 4. Sanitization: Absent; the skill does not specify any validation or sanitization of the input file names before execution.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 10:56 AM