The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions for the AI agent to follow and does not include any scripts, binaries, or external resources.
[NO_CODE]: No executable code is provided within this skill, which eliminates risks related to remote code execution, command injection, or persistence mechanisms.
[PROMPT_INJECTION]: The skill processes user tasks via the {{args}} parameter. This represents a potential surface for indirect prompt injection, though the risk is handled by the agent's underlying safety guardrails.
Ingestion points: User-supplied tasks are interpolated directly into the SKILL.md file via the {{args}} template variable.
Boundary markers: The prompt does not include explicit delimiters or instructions to prevent the agent from following commands that might be embedded within the user task.
Capability inventory: The skill instructions imply file management capabilities (inspect, edit, convert), which are standard operations for a document-focused agent.
Sanitization: No specific sanitization or validation of the input content is performed within the skill definition.

documents