The Agent Skills Directory

Prompt Injection (SAFE): No instructions were found that attempt to override AI behavior, bypass safety filters, or extract system prompts. The content is purely technical and instructional.
Data Exposure & Exfiltration (SAFE): There are no hardcoded credentials, sensitive file path accesses (e.g., .ssh, .aws), or unauthorized network operations. The saveCanvas function is a standard p5.js utility for local file saving.
Obfuscation (SAFE): The code is written in clear, human-readable JavaScript with no evidence of Base64 encoding, zero-width characters, or homoglyph attacks.
Unverifiable Dependencies & Remote Code Execution (SAFE): The script does not perform any external package installations (npm/pip) or execute remote scripts via curl/wget. It relies on local logic and standard p5.js functions.
Dynamic Execution (SAFE): No use of dangerous sinks such as eval(), exec(), or Function() was detected. Parameter updates use safe object property assignments.
Indirect Prompt Injection (SAFE): While the skill defines a surface for parameter updates (updateParameter), it lacks the capabilities (like file writes or network sends) and the ingestion of untrusted data required to facilitate an indirect injection attack.

algorithmic-art