The Agent Skills Directory

[SAFE]: The skill's primary function is to construct URLs for a well-known, public meme generation service. Analysis of the scripts and instructions shows no evidence of malicious intent, credential harvesting, or unauthorized system access.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest text from the agent's context to populate meme templates. This represents a potential surface for indirect prompt injection if the agent is tasked with generating memes from untrusted external sources (e.g., summarizing a malicious webpage). However, the output is restricted to image URLs, and the helper script correctly sanitizes input.
Ingestion points: Natural language requests and text inputs intended for meme captions (SKILL.md, README.md).
Boundary markers: Absent; the skill relies on the agent's internal logic to separate instructions from data.
Capability inventory: Generates URL strings; no direct network requests, file writes, or shell command execution in the provided scripts.
Sanitization: Employs urllib.parse.quote in scripts/meme_generator.py to escape characters and prevent URL injection.

meme-factory