The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides numerous examples and instructions for using the belt CLI tool to execute specialized applications such as search-assistant, agent-browser, and python-executor. These commands are standard for the platform's ecosystem and align with the skill's purpose.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it is designed to ingest and act upon data from external, untrusted websites.
Ingestion points: External data enters the agent context through the use of tavily/search-assistant, exa/search, and infsh/agent-browser which visit and extract content from competitor websites (SKILL.md).
Boundary markers: There are no explicit boundary markers or instructions to the agent to disregard potential commands found within the scraped web content.
Capability inventory: The skill is granted the Bash tool and uses the belt CLI, providing the capability to execute shell commands, run Python code, and perform further network operations (SKILL.md).
Sanitization: The skill does not implement or describe any sanitization, filtering, or validation steps for the content retrieved from the web before it is processed.

competitor-teardown