The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a potential surface for adversarial instructions to reach the agent.
Ingestion points: Untrusted data enters the agent context through endpoints such as google_reviews, organic_serp, and multi_platform_reviews as documented in SKILL.md.
Boundary markers: The documentation does not suggest the use of specific delimiters or safety instructions to isolate external content from the agent's primary instructions.
Capability inventory: The skill performs network operations by communicating with the mcp.localseodata.com server.
Sanitization: There is no mention of sanitization or filtering logic for the strings retrieved from external web sources.

localseodata-tool