loading
loading
Detect and neutralize prompt injection attempts before they reach your agent.
A lightweight first filter for obvious injection attempts. Honest caveat: detection alone is unreliable — pair it with prompt-injection-shield for real defense.
Listed for review
No verified public repo for this skill yet, so this page does not give you an install command. Skills with a verified source install in one command — or fully manual: copy the skill folder into .claude/skills/ and your agent picks it up.
Boostor Quality Score
84/100 · B
Prompt Injection Detector runs a fast, lightweight classifier on all untrusted input before it enters the agent context, flagging patterns consistent with jailbreak and indirect injection attacks. Blocked inputs are quarantined with an explanation log for audit purposes. Configurable sensitivity levels let you balance security against false positives.
Review an agent's logging so a production failure can be replayed without exposing secrets.
Sets the bar at replaying a real failure from the trace without leaking secrets — and catches teams logging cost but not per-step cause.
Transparent + deterministic: every point above is computed from this skill's real fields plus a prompt-injection safety scan. No black box, no pay-to-rank.
Keep long-running agents under token limits without losing critical state.
The fix for the wall every long-running agent hits — it summarizes old turns before the context window blows, instead of crashing mid-task.
Scaffold, test, and publish a Model Context Protocol server in minutes.
Writing an MCP server by hand means hours of boilerplate before the first tool runs. This validates against the spec so you skip the silent-failure stage.