The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized remote code execution attempts were detected in the skill instructions or metadata. The skill's behavior aligns with its stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its processing of external user narratives. 1. Ingestion points: User-provided narratives during Phase 1 (SKILL.md). 2. Boundary markers: No explicit delimiters are used to wrap or isolate user-provided data. 3. Capability inventory: The skill utilizes tools such as Read, Grep, Glob, WebFetch, and WebSearch. 4. Sanitization: No sanitization of input data is defined in the instructions. The risk is considered inherent to the classification task and is not indicative of malicious intent.

game-classifier