The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @tiny-fish/cli package via NPM. This is a vendor-owned resource used to provide the skill's primary functionality.
[COMMAND_EXECUTION]: The skill instructs the agent to execute various tinyfish CLI commands (search, fetch, agent, browser) to perform web-based research and automation tasks.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites, which could potentially contain malicious instructions aimed at the agent.
Ingestion points: Untrusted data enters the agent context through the outputs of tinyfish fetch and tinyfish agent commands, as described in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or provide warnings to the agent to ignore instructions embedded in the fetched web content.
Capability inventory: The skill facilitates browser automation and content extraction, which could be manipulated if the agent follows instructions found on external pages.
Sanitization: There is no description of sanitization, filtering, or validation performed on the data retrieved from external URLs.

use-tinyfish