The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the infsh CLI for authentication (infsh login) and tool execution (infsh app run).
[REMOTE_CODE_EXECUTION]: The skill triggers the execution of remote logic via the infsh app run command, invoking applications such as falai/flux-dev-lora, tavily/search-assistant, and exa/search. These tools run on infrastructure managed by third-party providers not included in the trusted vendor list.
[EXTERNAL_DOWNLOADS]: The skill documentation references external setup instructions and repository content hosted on GitHub at github.com/inference-sh/skills.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting data from web search providers (Tavily and Exa).
Ingestion points: External data enters the agent's context through the output of tavily/search-assistant and exa/search tools as described in SKILL.md.
Boundary markers: Absent. The instructions do not define delimiters or provide 'ignore instructions' warnings to the agent when processing search results.
Capability inventory: The agent has the ability to execute shell commands and trigger remote application logic via the infsh tool.
Sanitization: Absent. The skill does not demonstrate any validation, filtering, or escaping of the content retrieved from external search tools.

product-hunt-launch