The Agent Skills Directory

[SAFE]: No prompt injection or behavior override instructions were detected. The skill maintains its intended role-play within the Ship-Learn-Next framework.
[SAFE]: The skill uses the Read and Write tools appropriately for its stated purpose of analyzing provided files and saving action plans. No access to sensitive system paths or credentials was found.
[SAFE]: No obfuscation techniques such as Base64, zero-width characters, or hex encoding were identified in the skill content.
[SAFE]: The skill does not include any remote code execution, package installations, or dynamic execution patterns. The shell block provided in the instructions is for illustrative purposes for the user to specify a file path.
[SAFE]: Although the skill ingests external data (Category 8), the risk is minimal as it processes content into structured markdown. Evidence chain: 1. Ingestion points: user-provided file paths processed in SKILL.md; 2. Boundary markers: absent; 3. Capability inventory: Read and Write tools utilized; 4. Sanitization: none identified, output is strictly informational markdown.

ship-learn-next