The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs the user to fetch installation resources and documentation from external sources, specifically raw.githubusercontent.com/inference-sh/skills.
[COMMAND_EXECUTION]: The skill utilizes the Bash(belt *) tool to execute commands for searching, logging in, and running specific applications like tavily/search-assistant and exa/search.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external websites to generate analysis, which introduces a surface for indirect prompt injection if the extracted content contains malicious instructions.
Ingestion points: Web content is ingested via the tavily/extract and exa/search tools as described in SKILL.md.
Boundary markers: The skill does not define specific delimiters or guardrail instructions to ensure the agent ignores potentially malicious commands embedded in the fetched search results.
Capability inventory: The agent has the ability to run shell commands via belt and interact with multiple search and data extraction APIs.
Sanitization: There is no evidence of content sanitization or validation performed on the external data before it is incorporated into the content brief generation process.

seo-content-brief