Install validated Codex plugins from trusted sources with quarantine validation, provenance, and rollback. Use when distribution and installation are the primary goals.
69%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./Plugins/plugin-factory/fixtures/budget-archive/2026-04-21/deferred-store/skills/infrastructure_ops/plugin-installer/SKILL.mdThe canonical home for this skill is plugin-installer in jscraik/Agent-Skills
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The agent installs plugins by fetching repository contents from GitHub via API requests, where external contributors can author the content of the repository files read by the agent.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.