The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external URLs provided by the user to perform SEO audits. This content enters the agent's context and could potentially influence its behavior if it contains malicious instructions. * Ingestion points: The skill uses curl to fetch content from user-specified URLs and domains (found in SKILL.md under TECH Framework sections). * Boundary markers: The instructions do not specify explicit delimiters or guardrails to isolate the fetched external content from the agent's internal logic. * Capability inventory: The skill has the ability to execute shell commands including curl, grep, sed, and npx (found in SKILL.md CLI Commands Reference). * Sanitization: No specific sanitization or filtering of the fetched content is described before it is analyzed by the agent.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx lighthouse to conduct performance and accessibility audits, which involves downloading and executing the Lighthouse tool from a well-known package registry.
[COMMAND_EXECUTION]: The skill provides various shell commands for the agent to execute, such as curl to fetch site data and grep or sed to extract specific tags and information.

seo-rank