@1892/design-md

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from an external GitHub repository (github.com/VoltAgent/awesome-design-md) that is not identified as a trusted or well-known source.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted markdown data and incorporates it into the agent's execution context.
  • Ingestion points: Remote DESIGN.md files are downloaded from the VoltAgent/awesome-design-md repository into the project root as specified in the 'Quickstart' section of SKILL.md.
  • Boundary markers: There are no protective delimiters or explicit instructions to ignore embedded prompts when the agent reads the downloaded file.
  • Capability inventory: The skill has access to powerful tools including Bash, Read, and Write, which could be abused if the agent obeys malicious instructions hidden in a design file.
  • Sanitization: The skill does not perform any validation or sanitization on the external markdown files before passing them to the agent for processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 05:07 PM