The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/cover_ab.py uses the subprocess module to call ffmpeg and ffprobe for extracting frames and metadata from video files. The implementation uses list-based arguments without shell=True, which is a secure practice that prevents shell injection attacks.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied product descriptions and selling points through a prompt template to generate marketing copy. This represents a potential surface for indirect prompt injection if an attacker provides data containing hidden instructions. However, this is a standard feature for this type of agent skill and does not include autonomous execution of processed instructions.
[EXTERNAL_DOWNLOADS]: The documentation in SKILL.md references and links to other repositories under the author's GitHub account (xianyu110). These are identified as legitimate vendor-owned resources related to the skill's primary purpose.

cover-title-ab