The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses the WebSearch and WebFetch tools to retrieve information from external websites. This is a core part of its functionality for researching market trends, technology, and competitor analysis. While these are legitimate tools, they involve ingesting data from unverified third-party sources.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content retrieved from the internet. If a fetched website contains malicious instructions designed to manipulate an AI, the agent's behavior could be influenced.
Ingestion points: Data enters the context through the results of the WebSearch and WebFetch tools used in Step 2.
Boundary markers: The instructions do not define clear delimiters or specific warnings to the model to ignore potential instructions embedded within the research data.
Capability inventory: The skill has access to WebSearch, WebFetch, and the Task tool, the latter of which allows it to spawn sub-agents for parallel processing.
Sanitization: There are no explicit instructions for sanitizing, escaping, or validating the content retrieved from external sources before it is analyzed in Step 3.

research-topics