The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external WordPress pages and possesses write capabilities, creating a potential surface for indirect prompt injection.
Ingestion points: The skill uses multiple tools like respira_analyze_seo, respira_analyze_aeo, and respira_scan_page_accessibility to read and process content from target web pages as defined in the SKILL.md workflow.
Boundary markers: There are no explicit instructions or delimiters mentioned to prevent the agent from being influenced by malicious instructions embedded within the audited page content.
Capability inventory: The skill has access to respira_update_element and respira_apply_accessibility_fixes, which allow it to write or modify elements on the WordPress site based on findings.
Sanitization: The instructions do not specify any sanitization, filtering, or validation of the content extracted from target pages before it is processed by the agent to generate fix recommendations or perform updates.

respira-site-audit