The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves fetching and processing data from external web sources, which creates a potential vector for indirect prompt injection where adversarial instructions hidden in website content could influence agent behavior.
Ingestion points: The instructions in SKILL.md and references/rule.md direct the agent to fetch robots.txt files and page HTML from external URLs during the SEO audit.
Boundary markers: No specific delimiters or safety instructions are provided to the agent to isolate the fetched external content from its internal execution logic.
Capability inventory: The skill utilizes network fetching capabilities and content parsing to evaluate SEO signals.
Sanitization: There is no mention of sanitizing, filtering, or escaping the content retrieved from external web servers before it is processed by the agent.

indexability-conflicts