The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the belt CLI tool within a Bash environment to run research applications such as tavily/search-assistant and infsh/agent-browser for gathering competitive intelligence.
[EXTERNAL_DOWNLOADS]: The skill instructs users to install the belt-sh/cli via NPM and references a CLI installation guide hosted on GitHub at raw.githubusercontent.com/inference-sh/skills.
[REMOTE_CODE_EXECUTION]: The skill includes a Python script that uses matplotlib to generate a positioning map. This script is executed via the infsh/python-executor application on the inference.sh platform.
[PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing external data from web searches and page extractions.
Ingestion points: External data is ingested through the outputs of tavily/search-assistant, exa/search, and tavily/extract.
Boundary markers: The instructions do not provide explicit delimiters or instructions to the agent to disregard potential instructions embedded within the retrieved search results.
Capability inventory: The agent has the ability to execute shell commands, run Python code, and perform network requests via the integrated research tools.
Sanitization: No specific sanitization or validation logic is present to filter content from external research sources before it is processed by the agent.

competitor-teardown