The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the belt CLI tool to execute various research and analysis applications, including tavily/search-assistant and infsh/agent-browser.
[EXTERNAL_DOWNLOADS]: References installation instructions for the required belt CLI from the vendor's official GitHub repository at raw.githubusercontent.com/inference-sh/skills.
[REMOTE_CODE_EXECUTION]: Employs a Python execution tool (infsh/python-executor) to run code for generating positioning maps. The code is provided as a template within the skill instructions.
[DATA_EXFILTRATION]: Ingests and processes data from arbitrary external URLs (competitor websites) and search engine results to perform teardowns and feature comparisons.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from the web.
Ingestion points: Web content retrieved via infsh/agent-browser, tavily/extract, and search results from tavily/search-assistant and exa/search (referenced in SKILL.md).
Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded in the retrieved web content.
Capability inventory: Includes shell command execution via the belt CLI and Python code execution via infsh/python-executor.
Sanitization: No evidence of sanitization or validation of the ingested external content before it is processed by the agent.

competitor-teardown