agent-safety
ericrisco
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RA…
DesignClaude Code
58GitHub
OPENAGENTSKILL / DIRECTORY
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
1–1 / 1
Results: 1
ericrisco
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RA…
Owner-curated external sources. Not filtered by the scores or compatibility controls above; excluded from GitHub rankings and automatic installation.
No external entries match this query.