The Agent Skills Directory

[SAFE]: The skill is entirely instruction-based, providing structured templates and design principles (like the 10/20/30 rule) for presentation creation. No network operations, remote script execution, or sensitive file access patterns were identified.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information regarding audience, goals, and brand assets to populate presentation templates. While it lacks specific sanitization or boundary markers for this data, the skill has no dangerous capabilities (such as shell execution, network exfiltration, or privileged file access) for an attacker to exploit. Ingestion points: Step 1 (Context gathering) in SKILL.md. Boundary markers: Absent. Capability inventory: Text and markdown generation only; no exploitable tools or system commands are present. Sanitization: Absent.
[SAFE]: All examples and templates provided in the skill use fictional data and placeholders for demonstration, and no hardcoded credentials or malicious obfuscation techniques were detected.

presentation-designer