The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs users to install and execute code from external sources using npx skills add belt-sh/cli and various modules from inference-sh/skills. Executing unverified packages from non-whitelisted repositories presents a risk of running malicious code.
[EXTERNAL_DOWNLOADS]: The skill documentation includes a link to an external installation script hosted on GitHub at raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute belt CLI commands. These operations include authentication (belt login) and running specialized agentic tools (belt app run) for search, HTML-to-image conversion, and social media management.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing external web data. 1. Ingestion points: Data is ingested via tavily/search-assistant and exa/search search tools. 2. Boundary markers: The provided templates do not include clear delimiters or instructions to ignore embedded commands in the retrieved data. 3. Capability inventory: The skill has network access and social media posting capabilities via the belt CLI. 4. Sanitization: No sanitization or filtering logic is provided for the external content before it is processed by the agent.

newsletter-curation