feat(post-mcp-verify): E14 part 2 — cumulative-drift MEDIUM advisory [skip-docs]

Wave C step C2: surface the cumulative-drift signal from
checkDescriptionDrift() (added in C1) as a separate MEDIUM advisory
with finding category mcp-cumulative-drift. Independent of the existing
per-update drift advisory — a slow-burn rug-pull that keeps each update
below the 10% per-update threshold but cumulatively drifts >=25% from
the sticky baseline now triggers the new advisory without ever crossing
the per-update bar.

The advisory references /security mcp-baseline-reset (added in C3) so
the user knows how to acknowledge a legitimate MCP server upgrade.

CLAUDE.md updates:
- post-mcp-verify hooks-table row mentions per-update + cumulative drift
- mcp-description-cache lib bullet documents baseline schema, history,
  cumulative threshold policy key, and LLM_SECURITY_MCP_CACHE_FILE
  override.

Tests: 2 new hook tests using LLM_SECURITY_MCP_CACHE_FILE for cache
isolation. Existing 68 still pass; total 70.

Plugin README and root marketplace README updates land in C3 alongside
the new /security mcp-baseline-reset slash command (combined Wave-C
doc update per plan §"Wave C — Touch" list).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

plugins/llm-security/CLAUDE.md

@@ -69,7 +69,7 @@ formula; resolution deferred to Batch B.
 | `pre-bash-destructive.mjs` | PreToolUse | `Bash` | Block rm -rf, curl\|sh, fork bombs, eval. Bash evasion normalization (T1-T6 via `bash-normalize.mjs`: empty quotes, ${} expansion, backslash splitting, IFS, ANSI-C hex) — defense-in-depth mot T1-T6; Claude Code 2.1.98+ dekker harness-nivå |
 | `pre-install-supply-chain.mjs` | PreToolUse | `Bash` | Block compromised packages across ALL ecosystems. Bash evasion normalization before gate matching |
 | `pre-write-pathguard.mjs` | PreToolUse | `Write` | Block writes to .env, .ssh/, .aws/, credentials, settings |
-| `post-mcp-verify.mjs` | PostToolUse | — (all) | Injection scan on ALL tool output (incl. MEDIUM patterns, HITL traps, sub-agent spawn, NL indirection, cognitive load, hybrid P2SQL/recursive/XSS). HTML content trap detection. Bash-specific: secrets/URLs/size. MCP: description drift detection (MCP05), per-tool volume tracking |
+| `post-mcp-verify.mjs` | PostToolUse | — (all) | Injection scan on ALL tool output (incl. MEDIUM patterns, HITL traps, sub-agent spawn, NL indirection, cognitive load, hybrid P2SQL/recursive/XSS). HTML content trap detection. Bash-specific: secrets/URLs/size. MCP: per-update description drift (MCP05) AND cumulative drift vs sticky baseline (E14, v7.3.0) — slow-burn rug-pulls that stay under the per-update threshold but diverge >=25% from baseline emit MEDIUM `mcp-cumulative-drift` advisory. Per-tool volume tracking |
 | `post-session-guard.mjs` | PostToolUse | — (all) | Runtime trifecta detection (Rule of Two). Sliding window (20 calls) + 100-call long-horizon. MCP-concentrated trifecta (same server = elevated severity). Sensitive path + exfil detection. Slow-burn trifecta (legs >50 calls apart = MEDIUM). Behavioral drift detection (Jensen-Shannon divergence). CaMeL-inspired data flow tagging (SHA-256 provenance tracking, output→input linking). Mode: `LLM_SECURITY_TRIFECTA_MODE=block\|warn\|off` (default: warn). Cumulative data volume tracking (100KB/500KB/1MB thresholds). Sub-agent delegation tracking (Task/Agent tools): escalation-after-input advisory when delegation occurs within `LLM_SECURITY_ESCALATION_WINDOW` calls (default 5) of untrusted input (DeepMind Agent Traps kat. 4); secondary 20-call MEDIUM advisory catches slow-burn variants outside the primary window (E17, v7.2.0) |
 | `update-check.mjs` | UserPromptSubmit | — | Checks for newer versions (max 1x/24h, cached). Disable: `LLM_SECURITY_UPDATE_CHECK=off` |
 
@@ -96,7 +96,7 @@ Post-clone: size check (100MB max), cleanup guarantee (temp dir + evidence file
 With `--output-file`: full JSON to file, compact aggregate to stdout. `--baseline` diffs against stored baseline. `--save-baseline` saves results for future diffs. Baselines stored in `reports/baselines/<target-hash>.json`.
 
 10 scanners: unicode, entropy, permission, dep-audit, taint, git-forensics, network, memory-poisoning, supply-chain-recheck, toxic-flow.
-Lib: `mcp-description-cache.mjs` — caches MCP tool descriptions in `~/.cache/llm-security/mcp-descriptions.json`, detects drift via Levenshtein (>10% = alert), 7-day TTL. Used by `post-mcp-verify.mjs`.
+Lib: `mcp-description-cache.mjs` — caches MCP tool descriptions in `~/.cache/llm-security/mcp-descriptions.json`, detects per-update drift via Levenshtein (>10% = alert), 7-day TTL. v7.3.0 (E14) adds a sticky baseline slot per tool plus a 10-event rolling history; cumulative drift = `levenshtein(current, baseline) / max(|current|,|baseline|)`. When ratio ≥ `mcp.cumulative_drift_threshold` (default 0.25), emits `mcp-cumulative-drift` advisory through `post-mcp-verify.mjs`. Baseline survives TTL purge so slow-burn drift is preserved across the 7-day window. `clearBaseline(tool?)` exposed for the `/security mcp-baseline-reset` command. `LLM_SECURITY_MCP_CACHE_FILE` env var overrides the cache path for testing.
 Supply-chain-recheck (SCR) re-audits installed dependencies from lockfiles (package-lock.json, yarn.lock, requirements.txt, Pipfile.lock) against blocklists, OSV.dev batch API, and typosquat detection. Offline fallback available. Shared data module: `scanners/lib/supply-chain-data.mjs`.
 Memory-poisoning (MEM) detects cognitive state poisoning in CLAUDE.md, memory files, and .claude/rules — injection patterns, shell commands, credential paths, permission expansion, suspicious URLs, encoded payloads.
 Toxic-flow (TFA) is a post-processing correlator that runs LAST — detects "lethal trifecta" (untrusted input + sensitive data access + exfiltration sink) by correlating output from prior scanners.