update-sf

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly runs "git pull origin main" on the repo path extracted from the user's shell alias (Paso 2: "Actualizar el repositorio fuente") and then copies the repo's .claude/ into the project (Paso 3), so content from potentially public/untrusted git remotes will be ingested and can alter the agent's tools/behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill runs "git pull origin main" at runtime to update a remote repository and then copies the repo's .claude/skills and AI templates into the project—meaning the remote git repository (the configured "origin" URL, e.g. git@github.com:org/saas-factory.git or https://github.com/org/saas-factory.git) is fetched at runtime and can directly control agent prompts and behavior.