# hippo_skill_exposure_audit

CYCLE #7 — empirical audit: per ogni candidate skill,

Agent View of the PolicyLayer registry record for `hippo_skill_exposure_audit`. HTML page: https://policylayer.com/tools/verimem/hippo-skill-exposure-audit

## Facts

- Tool: `hippo_skill_exposure_audit`
- Server: Verimem (`aureliocpr-ctrl/verimem`) — https://policylayer.com/tools/verimem.md
- Homepage: https://github.com/aureliocpr-ctrl/verimem
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "hippo_skill_exposure_audit",
    "arguments": {}
  }
}
```

## Why hippo_skill_exposure_audit is rated Low

This is an auditing and assessment tool that retrieves or analyzes information about skill exposure. It reads and evaluates data but does not modify state, execute external commands, delete data, or create financial obligations. The blast radius of misuse is minimal—an AI agent could retrieve audit information it shouldn't see, but cannot damage systems or data through this tool alone.

From the tool's own definition: "Tool name 'hippo_skill_exposure_audit' and description indicate an 'empirical audit' function that examines/evaluates candidate skills. The term 'audit' implies inspection and analysis without modification."

## Use case

AI agents call hippo_skill_exposure_audit to retrieve information from Verimem without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Verimem:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "hippo_skill_exposure_audit": {}
  }
}
```

## Other tools on Verimem (236)

- `hippo_fact_forget` — Destructive — https://policylayer.com/tools/verimem/hippo-fact-forget.md
- `hippo_fact_forget_with_undo` — Destructive — https://policylayer.com/tools/verimem/hippo-fact-forget-with-undo.md
- `hippo_forget` — Destructive — https://policylayer.com/tools/verimem/hippo-forget.md
- `hippo_forget_scope` — Destructive — https://policylayer.com/tools/verimem/hippo-forget-scope.md
- `hippo_skill_archive` — Destructive — https://policylayer.com/tools/verimem/hippo-skill-archive.md
- `hippo_skill_retire` — Destructive — https://policylayer.com/tools/verimem/hippo-skill-retire.md
- `hippo_compose_plan` — Execute — https://policylayer.com/tools/verimem/hippo-compose-plan.md
- `hippo_consolidate` — Execute — https://policylayer.com/tools/verimem/hippo-consolidate.md
- `hippo_curate_pipeline` — Execute — https://policylayer.com/tools/verimem/hippo-curate-pipeline.md
- `hippo_decay_run` — Execute — https://policylayer.com/tools/verimem/hippo-decay-run.md
- `hippo_plan_strips` — Execute — https://policylayer.com/tools/verimem/hippo-plan-strips.md
- `hippo_provider_switch` — Execute — https://policylayer.com/tools/verimem/hippo-provider-switch.md
- `hippo_reason` — Execute — https://policylayer.com/tools/verimem/hippo-reason.md
- `hippo_rollout_actions` — Execute — https://policylayer.com/tools/verimem/hippo-rollout-actions.md
- `hippo_run_task` — Execute — https://policylayer.com/tools/verimem/hippo-run-task.md
- `hippo_skill_compile_macro` — Execute — https://policylayer.com/tools/verimem/hippo-skill-compile-macro.md
- `hippo_skill_derive_predicates` — Execute — https://policylayer.com/tools/verimem/hippo-skill-derive-predicates.md
- `hippo_skills_derive_predicates_batch` — Execute — https://policylayer.com/tools/verimem/hippo-skills-derive-predicates-batch.md
- `hippo_world_simulate` — Execute — https://policylayer.com/tools/verimem/hippo-world-simulate.md
- `sandbox_exec` — Execute — https://policylayer.com/tools/verimem/sandbox-exec.md
- `hippo_dream_propose` — Other — https://policylayer.com/tools/verimem/hippo-dream-propose.md
- `hippo_agent_specialization` — Read — https://policylayer.com/tools/verimem/hippo-agent-specialization.md
- `hippo_agent_workload` — Read — https://policylayer.com/tools/verimem/hippo-agent-workload.md
- `hippo_anchor_recall` — Read — https://policylayer.com/tools/verimem/hippo-anchor-recall.md
- `hippo_anti_confab_scan` — Read — https://policylayer.com/tools/verimem/hippo-anti-confab-scan.md
- `hippo_assess_confidence` — Read — https://policylayer.com/tools/verimem/hippo-assess-confidence.md
- `hippo_assess_fact_freshness` — Read — https://policylayer.com/tools/verimem/hippo-assess-fact-freshness.md
- `hippo_audit_summary` — Read — https://policylayer.com/tools/verimem/hippo-audit-summary.md
- `hippo_audit_tail` — Read — https://policylayer.com/tools/verimem/hippo-audit-tail.md
- `hippo_briefing` — Read — https://policylayer.com/tools/verimem/hippo-briefing.md
- …and 206 more: https://policylayer.com/tools/verimem.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=verimem · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/verimem