The Agent Skills Directory

[SAFE]: The skill provides reference guides, code patterns, and performance optimization strategies. No malicious scripts, exfiltration attempts, or unauthorized access patterns were identified in the content.- [PROMPT_INJECTION]: The Delegation section in SKILL.md outlines tasks where an agent is instructed to audit external HTML and perform automated conversions. This creates an indirect prompt injection surface where a malicious website could include instructions intended to influence the agent's behavior. Ingestion points: External HTML pages scanned by the Explore agent. Boundary markers: None specified in the documentation. Capability inventory: Reading and analyzing HTML content, planning optimization workflows, and rewriting image tags. Sanitization: No sanitization or instruction-ignoring delimiters are mentioned for processing external content.

responsive-images