The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted content from external websites.
Ingestion points: The agent fetches content from competitor_url using web_fetch and processes data from multiple web_search queries in Steps 1, 2, 3, and 4 of SKILL.md.
Boundary markers: There are no explicit delimiters or instructions telling the agent to treat the fetched content as data only and to disregard any instructions found within it.
Capability inventory: The skill utilizes web_search and web_fetch to retrieve external data.
Sanitization: No sanitization or filtering mechanisms are described to clean the content fetched from competitor sites before it is processed by the agent.

competitor-spy