fixing-accessibility

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.65). The required workflow is to install and invoke the community skill ibelick/ui-skills from a public GitHub package; at runtime the agent will fetch and execute that outsider-authored skill code/content, which can ingest free-form text (e.g., from the skill’s own prompts or fetched pages) into the LLM context, creating indirect prompt-injection risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill's install step (npx skills add ibelick/ui-skills --skill fixing-accessibility) fetches and installs code from the external repository (https://github.com/ibelick/ui-skills / npm package ibelick/ui-skills) at runtime, which would execute remote skill code required to run the skill.