Agent skill · security · github
verify-agent-action
Review a proposed AI-agent action or human-approval packet before execution. Use when an agent wants to run a consequential tool, command, deployment, message, purchase, credential operation, or data mutation; when checking whether approval still matches the exact action; or when auditing action evidence for forged results, parameter swaps, replay, correlated reviewers, missing evidence, expiry, or stale monitoring. Produce an evidence-based review only—never execute or authorize the action.
Why this skill is useful
Adds a comprehensive review process for verifying AI agent actions, ensuring safety and integrity through detailed checks and evidence collection.
What it needs
About 5k tokens when loaded. Last updated 2026-08-07. 37,534 stars on the source repository.
What this skill does
Verify Agent Action Treat a plausible approval screen as a claim, not proof. Verify the complete decision path before a human or an external enforcement point decides whether to act. Preserve the safety boundary Never execute, approve, sign, send, purchase, deploy, or mutate anything. Never convert this review into execution authority. Never infer missing evidence, identities, timestamps, or parameters. Treat a valid schema, checksum, or signature as insufficient by itself. Treat signatures as evidence of attribution and integrity, not factual truth. Keep supporting and refuting evidence separate; do not average conflict away. Fail closed on a material mismatch. Use INCONCLUSIVE when required evidence is unavailable. Set this field in every final result: Collect the review packet Request only the artifacts needed for the review: 1. The original user or system request. 2. The exact proposed action: operation or tool name target resource complete parameters filesystem and network scope maximum execution count not-before and expiry times 3. The assessment that claims the action is justified. 4. The source evidence and policy used by that assessment. 5. The approval record, including approver identity, role, action digest, nonce, audience, issue time, expiry, and use count. 6. The latest monitoring events and expected heartbeat interval. 7. The current trusted time and any prior nonce-use record. List missing fields before analysis. Do not silently substitute defaults. Build the exact action identity Create one normalized action object without dropping fields: Use a project-specified canonicalization and digest algorithm when provided. Otherwise, report that cryptographic identity cannot be independently verified; still compare every field structurally. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills github/verify-agent-action