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.
Turn onboard deficiencies, PSC findings, Class observations, and ISM/ISPS/MLC audit issues into professional maritime corrective-action replies, CAPA reports, evidence checklists, and close-out summaries.
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.
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.
Scan AI Skills and MCP servers before installation. Detect risky scripts, permissions, dependencies, network access, credential exposure, file changes, and suspicious configurations — then generate a clear evidence-based security report.
I built this Skill to help users protect API keys, OAuth tokens and MCP credentials when working with AI agents in Codex Desktop, Claude Desktop and local automation environments. It combines static leak detection, vault preflight checks, runtime redaction, MCP-safe remediation, credential-store guidance and security reporting. The Skill is designed to reduce accidental secret exposure while preserving legitimate MCP and API workflows.
Catches cascade failures that partial checks miss — pre-check names the risk before editing, post-check demands evidence values after, then auto-repairs in a loop while rereading the entire file every cycle until zero errors remain.
A monthly co-pilot for prop-firm traders: turn a discretionary method into an EA spec, implement it in MT5 (MQL5; MT4/MQL4 conversion), and design a Compliance Guard that halts the EA before it breaks firm rules (drawdown, lot, trading hours). The skill refuses unsafe requests (no stop-loss, unlimited martingale, guaranteed returns, target win rates) and requires risk limits and disclaimers. Not investment advice; no guarantee of passing.