claude-gif-generate

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute several local scripts (e.g., generate.py, gif_convert.sh, gif_loop.py) for media processing. These scripts are invoked with arguments derived from user input.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection vulnerability surface where untrusted user input is passed to system commands. \n
  • Ingestion points: User-defined GIF descriptions enter the context through natural language prompts and are interpolated into the --prompt argument of the generate.py script. \n
  • Boundary markers: Absent. The skill instructions do not provide delimiters or instructions for the agent to escape or ignore malicious instructions embedded in the user prompt. \n
  • Capability inventory: The skill has access to the Bash tool and local Python interpreters, enabling it to execute commands, write to the filesystem (/tmp, ~/Documents), and likely perform network operations via the Google Veo API scripts. \n
  • Sanitization: Absent. There is no visible logic or instruction to sanitize the user input for shell metacharacters before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 12:50 AM