The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and evaluate external web content, which constitutes an attack surface for indirect prompt injection.
Ingestion points: The skill instructions guide the agent to fetch external pages (homepage, blog posts, etc.) using WebFetch or curl for evaluation.
Boundary markers: There are no specific instructions or delimiters provided to isolate the fetched content from the agent's internal reasoning or to prevent the agent from following instructions embedded in the target content.
Capability inventory: The skill uses Bash, WebFetch, and Write (to generate the GEO-CONTENT-ANALYSIS.md report).
Sanitization: The instructions do not include steps for sanitizing or escaping the data retrieved from external URLs before processing it.

geo-content