The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and analyze content from arbitrary external URLs using an AI model. This creates a surface for indirect prompt injection attacks where content retrieved from the web could contain hidden instructions designed to manipulate the agent's output or actions.
Ingestion points: External web content is ingested into the agent context via the nansen web fetch command described in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to the AI to ignore instructions embedded within the fetched data.
Capability inventory: The skill is authorized to use the Bash(nansen:*) tool, allowing it to execute CLI commands to interact with web resources.
Sanitization: No sanitization or filtering logic is specified for the content retrieved from external URLs.
[COMMAND_EXECUTION]: The skill relies on executing the nansen CLI tool via Bash to perform its primary functions, including web searching and fetching. This involves the execution of shell commands on the system where the agent is running.
[EXTERNAL_DOWNLOADS]: The skill's configuration in SKILL.md specifies the installation of the nansen-cli package from the Node.js package registry. This is a vendor-provided tool required for the skill's operation.

nansen-web-fetcher