Audit the memory and instruction files your AI agent reads (AGENTS.md, CLAUDE.md, LEARNINGS.md, system prompts). A bundled offline Python script finds pasted secrets, injected instructions, hidden characters, risky commands, contradictions, duplicates, stale entries and broken file references, and writes cleaned copies. Download package: you bring your own AI agent and Python 3; no model is included.
Keeps your AI agent from forgetting who it is. Detects and neutralizes persona drift, rule erosion, and prompt injection attempts — across long conversations. Context isolation, anti-drift enforcement, and graceful override responses built in. Your custom persona stays locked.
Tidy any folder on your computer. An AI agent reads each file and renames it by real date, type and counterparty, e.g. 2025-02-05_invoice_acme_123.pdf. You review and edit everything in a local browser page before anything changes, can sort files into folders, and find them later by type, counterparty or year. Every session can be undone. Runs on your computer with Claude Code, Codex or OpenClaw; needs Python 3.8+.
Audit AI agents, Skills, MCP configurations, tool permissions, and coding-agent setups for prompt injection, excessive agency, credential exposure, data leakage, unsafe code execution, supply-chain risks, memory risks, missing approval controls, and runaway autonomy. Get a calibrated Security Score, Audit Confidence, evidence-backed findings, remediation steps, verification checks, and residual-risk analysis.
Analysez logs, diagnostics, erreurs et éléments techniques fournis afin d’identifier des causes probables, prioriser les anomalies et préparer un plan de correction.
This Skill is built on practical expertise in AI agent safety, prompt-injection defense, source-to-sink privacy review, tool and MCP metadata integrity, memory provenance checks, autonomous action scoping, and evidence-based verification. It helps agents separate instructions from evidence before tool calls, uploads, publishing, deletion, code execution, or network output.
