The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external search services (Tavily and Exa), creating a potential surface for indirect prompt injection where malicious instructions in search results could influence the agent's behavior.
Ingestion points: Untrusted content is ingested from tavily/search-assistant, tavily/extract, and exa/search and interpolated into the content brief generation process.
Boundary markers: The skill lacks explicit boundary markers or "ignore embedded instructions" warnings when processing these search results.
Capability inventory: The skill has access to the Bash tool to execute belt CLI commands, which could be abused if the agent is manipulated by injected data.
Sanitization: There is no evidence of automated sanitization or filtering for the data retrieved from external search engines.
[EXTERNAL_DOWNLOADS]: The skill references external tools and documentation hosted on the vendor's infrastructure.
Evidence: Mentions installation of the belt-sh/cli package via npx and references installation instructions located at raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
[COMMAND_EXECUTION]: The skill is designed to execute shell commands using the belt CLI through the Bash tool to perform keyword research and SERP analysis.

seo-content-brief