The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the open web, which could contain instructions designed to manipulate the agent's output.
Ingestion points: The skill performs web_search operations in Step 2 to gather data from official affiliate pages and network listings.
Boundary markers: Absent. The instructions do not include specific delimiters or directives to the agent to ignore potentially malicious instructions found within the search results.
Capability inventory: The skill utilizes web_search to retrieve external data and produces structured markdown for user review.
Sanitization: Step 5 includes logic to validate the format and domain of user-provided affiliate links, though it does not sanitize the content retrieved via search results.
[EXTERNAL_DOWNLOADS]: The skill interacts with external sites and repositories as part of its primary function.
The skill fetches information from various external affiliate networks and pricing pages via web search.
It encourages users to contribute findings to the vendor's official GitHub repository (Affitor/affiliate-skills) and the community directory (openaffiliate.dev).

submit-program