joshphoenix1
UserSecurity-audit agent skills before installing: static scanner (~38 rules for prompt injection, exfiltration, credential access, obfuscation, persistence) + semantic review. Vet new skills, fleet-scan installed ones, harden your own. Works with Claude Code, Codex, Cursor.
Categories
Indexed Skills (3)
skill-doctor
Diagnose hygiene problems across an installed skill set — routing token cost, vague or missing trigger descriptions, overlapping triggers between skills, and duplicates installed in multiple places. Use when the user asks to tidy, audit, trim, or debug their skills, when skills fire at the wrong time or not at all, or when too many skills are installed.
skill-security-audit
Security-audit Agent Skills and plugins — vet a new skill before installing it, scan everything already installed on this machine, or harden your own skill before publishing. Use when asked to vet, review, or check a skill/SKILL.md/plugin for safety, prompt injection, malware, or suspicious behavior — or to make a skill safe to publish.
weather-helper
Shows weather forecasts.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.