claude-gif-generate

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a sequence of local scripts for video generation (generate.py), format conversion (gif_convert.sh), and GIF optimization (gif_loop.py, gif_optimize.py). The scripts are invoked via an absolute path to a specific Python environment (~/.video-skill/bin/python3) or shell interpreter.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate the content for the AI video prompts.
  • Ingestion points: User-provided descriptions of the desired GIF (documented in Step 3 and Step 5).
  • Boundary markers: Absent; the user's concept is directly incorporated into the command-line arguments for the generation script.
  • Capability inventory: The skill utilizes Bash for script execution and Read for accessing reference files.
  • Sanitization: No explicit sanitization or validation of the user's input string is performed before it is passed to the generation command.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 07:47 AM