The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install external tools and related skills. It references npx skills add belt-sh/cli and several skills from the inference-sh organization on GitHub. It also provides a link to installation instructions hosted at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
[COMMAND_EXECUTION]: The skill uses the belt CLI to run various AI applications via Bash. These include image generation (falai/flux-dev-lora), text-to-speech (falai/dia-tts), and video creation (google/veo-3-1-fast). It also demonstrates social media automation through commands like belt app run x/post-create.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and reformat external content (blogs, podcasts, videos), making it susceptible to indirect prompt injection if the source data contains malicious instructions.
Ingestion points: Processes long-form source content provided in files or as input variables.
Boundary markers: The instructions lack explicit delimiters or guidance to ignore instructions embedded within the processed content.
Capability inventory: The skill can execute shell commands, access the network via AI apps, and post to external social media accounts.
Sanitization: No input sanitization or validation mechanisms are mentioned.

content-repurposing