The Agent Skills Directory

[Prompt Injection] (SAFE): No behavioral overrides, safety bypasses, or instructions to reveal system prompts were found. All instructions are focused on graphic design.- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network operations were identified.- [Obfuscation] (SAFE): No Base64 encoding, zero-width characters, homoglyphs, or other obfuscation techniques were detected.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external package installations (pip, npm) or remote script execution (curl | bash) are present.- [Privilege Escalation] (SAFE): No commands for elevating user privileges or modifying system files were found.- [Indirect Prompt Injection] (LOW): The skill provides templates that interpolate user input into image generation prompts (e.g., [subject], [topic]). While this is an injection surface for malicious data to influence the final prompt, the skill lacks dangerous capabilities like code execution or file writes, limiting the impact to the generated text/image content.- [Dynamic Execution] (SAFE): No use of eval(), exec(), or runtime code generation was detected.

social-graphics