The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves and displays article bodies and summaries from an external feed (Amazon seller policies via LinkFox gateway). This content is interpolated into the agent context, creating a surface for potential tool output poisoning.
Ingestion points: The script amazon_policy_feed_detail.py fetches full article bodies in Markdown format from the linkfox.com gateway.
Boundary markers: The instructions direct the agent to render the output as-is, without protective delimiters or instructions to ignore embedded commands.
Capability inventory: The skill possesses network access and file system write capabilities for logging and caching.
Sanitization: The scripts do not perform explicit sanitization or filtering of the retrieved external content before presentation.
[EXTERNAL_DOWNLOADS]: The skill scripts perform network requests to LinkFox subdomains, including tool-gateway.linkfox.com, api.linkfox.com, and agent-api.linkfox.com, for policy data retrieval and user account management. These represent vendor-owned infrastructure.
[COMMAND_EXECUTION]: The skill includes documentation and a script (onboarding.py) that guides users to execute shell commands to persist environment variables for API key configuration.

linkfox-amazon-policy-feed