The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and evaluate untrusted data from external websites, creating a surface for indirect prompt injection.
Ingestion points: Instructions in SKILL.md direct the agent to retrieve and analyze external content including robots.txt files, XML sitemaps, and on-page metadata from URLs provided by the user.
Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore potentially malicious instructions embedded in the website's HTML comments or meta tags.
Capability inventory: The agent intended to use this skill typically possesses network access tools (like curl) and file system access, which could be leveraged if the agent inadvertently follows instructions hidden in the audited content.
Sanitization: No sanitization or validation steps are provided for the data fetched from the external sites before the agent processes it.

seo-audit