The Agent Skills Directory

Prompt Injection (SAFE): No patterns of instruction override, jailbreak attempts, or safety filter bypasses were detected in the skill instructions or metadata.\n- Data Exposure & Exfiltration (SAFE): The skill does not contain any commands for file system access, credential harvesting, or network communication to external domains.\n- Unverifiable Dependencies & Remote Code Execution (SAFE): No scripts, package managers, or remote execution patterns (curl|bash) are present in the skill files.\n- Obfuscation (SAFE): No Base64, zero-width characters, homoglyphs, or other encoding techniques were found that could hide malicious intent.\n- Indirect Prompt Injection (LOW): The skill processes external 'Source Material' as input. While there are no explicit delimiters or sanitization steps mentioned, the skill lacks any 'capabilities' (e.g., shell access, network ops) that could be exploited by instructions embedded within that material. (Evidence: Ingestion: Source Material in SKILL.md; Boundary Markers: Absent; Capability Inventory: None; Sanitization: Absent).

quiz-creator