fal-ai-skills

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow is installing and invoking the bundled fal-generate skill from the public fal-ai-community/skills package registry (via npx skills add), which can fetch and ingest outsider-authored skill code/content at runtime into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The listed install command (npx skills add fal-ai-community/fal-generate) will fetch and execute remote package code at runtime (sourced from the upstream repo https://github.com/fal-ai-community/skills / the npm registry), so it is a required external dependency that executes remote code.