PraisonAI's template loader accepts GitHub template URIs with refs, for example "github:owner/repo/template@v1.0.0". The resolver stores the user-controlled template path and ref verbatim, and the cache layer later joins those values into "~/.praison/cache/templates/github/<owner>/<repo>/<template>/<ref>" without normalizing each segment or checking that the final path remains inside the template cache root. A crafted ref such as "../../../../../../outside-delete-target" therefore escapes the cache directory. The first load can write ".cache_meta.json" outside the cache. If the normal cache hierarchy for the same owner/repo/template has already been created, the same path reaches "shutil.rmtree(cache_path)" and removes an attacker-selected outside directory before replacing it with cache metadata. This is distinct from the old template Zip Slip advisory. No malicious archive member is needed, and the PoV disables network access entirely. The bug is in cache-key construction for GitHub template URIs.