algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to derive conceptual seeds that influence the generation of executable p5.js code within an HTML artifact.
- Ingestion points: User instructions are processed in SKILL.md to form the basis of the 'algorithmic philosophy' and code parameters.
- Boundary markers: Absent; no delimiters or warnings are specified for the ingested user-provided data.
- Capability inventory: The skill generates executable JavaScript code and content in markdown files.
- Sanitization: Absent; there is no logic for escaping or validating user-provided conceptual input before interpolation into generated scripts.
- [EXTERNAL_DOWNLOADS]: The viewer.html template fetches the p5.js library from Cloudflare's public CDN (cdnjs.cloudflare.com). This is documented as a neutral finding involving a well-known service.
- [METADATA_POISONING]: The SKILL.md instructions mandate the agent to repeatedly use deceptive language in its output to misrepresent the AI's generated work as the product of 'master-level' human craftsmanship and 'countless hours' of optimization.
Audit Metadata