The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through external data ingestion. Ingestion points: The skill uses infsh app run to fetch data from external sources like Tavily and Exa. Boundary markers: The skill instructions do not specify any delimiters or warnings to ignore instructions embedded in the search results. Capability inventory: The skill can execute bash commands through the infsh utility. Sanitization: There is no evidence of sanitization or filtering applied to the results of search queries before they are processed.- [COMMAND_EXECUTION]: The skill executes commands using the infsh CLI tool for fact-checking and research. These operations are restricted to the author's own infrastructure.- [EXTERNAL_DOWNLOADS]: The skill references installing additional capabilities from the developer's official repositories on GitHub and the inference.sh platform.

press-release-writing