Back to skill

Security audit

MuninnDB Auto Memory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local memory integration, but it automatically persists session/project context and can install a recurring snapshot job that collects local metadata without enough user control.

Install only if you intentionally want an always-on MuninnDB memory layer and are comfortable with automatic cross-session persistence. Avoid enabling the cron snapshot unless you understand that it will repeatedly store hostname, working directory, and recent Hermes session metadata; use a narrowly scoped token, review vault contents regularly, and confirm how to pause/remove the scheduled job.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (3)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:10
Finding

Automatic Persistent Context Injection and Memory Poisoning

Content
View full analysis
Remediation
View remediation

T06 · System Persistence

Error
Location
references/setup-companion.md:85
Finding

Recurring Cron Job Creates Cross-Session Persistence

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
scripts/muninndb-memory-snapshot.sh:16
Finding

Recurring Collection of Credentials, Host Context, and Agent Session Metadata

Content
View full analysis
/dev/null || echo "") VAULT="hermes" HOSTNAME=$(hostname -s 2>/dev/null || echo "unknown") TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ") # Pruefe ob MuninnDB laeuft HEALTH=$(curl -s -o /dev/null -w "%{http_code}" "$MUNINN_URL/api/health" 2>/dev/null) if [ "$HEALTH" != "200" ]; then exit 0 # silent fail fi # Aktuelles Verzeichnis + letzte Session-Info CWD=$(pwd) RECENT_SESSIONS=$(hermes sessions list --limit 3 2>/dev/null || echo "n/a") SUMMARY="Cron-Snapshot von $HOSTNAME um $TIMESTAMP Working Directory: $CWD Letzte Sessions: $RECENT_SESSIONS" # In MuninnDB speichern RESULT=$(curl -s -X POST "$MUNINN_URL/api/engrams" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $MUNINN_TOKEN" \ -d "$(jq -n --arg c "cron-snapshot-$HOSTNAME" --arg x "$SUMMARY" \ '{concept: $c, content: $x, vault: "hermes", tags: ["cron","snapshot","'$HOSTNAME'"], type: "event"}')" 2>/dev/null) ``` ### Technical Analysis The recurring script reads the bearer token from `~/.muninn/openclaw.key`, obtains the short hostname and current working directory, and invokes `hermes sessions list --limit 3` to collect recent agent-session information. It combines these values into a summary and stores the summary in the persistent `hermes` vault. The destination is hardcoded to `127.0.0.1`, so the audited code does not demonstrate direct transmission to an external host. Nevertheless, the implementation creates a recurring historical record of host identity, execution location, and recent agent activity. Anyone who can read the vault or compromise the local MuninnDB service may access that accumulated information. The bearer token is also made available to eve ...[truncated 1515 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Findings (27)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared purpose says this is an automatic MuninnDB memory layer via MCP, but the body adds materially broader behaviors: periodic cron execution, secret reading from disk, session/host/workdir collection, external CLI invocation, and direct REST writes. This mismatch is dangerous because users and policy systems may authorize the skill under a much narrower trust model than what it actually instructs the agent to do.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill directs automatic storage of user preferences, decisions, project context, fixes, and summaries without an explicit privacy notice, retention policy, or consent flow. This can lead to unauthorized persistence of sensitive or confidential information across sessions.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The periodic snapshot section describes collection of system and session metadata but does not clearly warn users that host, session, and working-directory context will be captured regularly. Hidden or under-disclosed metadata collection is particularly risky because it may reveal internal project names, machine identity, or operational details.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill relies on shell-capable behavior via cron management, local file reads, and curl examples, yet it declares no explicit tool scope or permissions boundary. This creates an authorization gap where a consumer may expect a simple MCP-memory skill, while the instructions actually require broader execution and filesystem/network capabilities.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction to 'always load' and act automatically has no scoping limits, exclusions, or sensitivity boundaries. Overly broad automatic activation can cause the skill to run in contexts where memory persistence or recall is inappropriate, including sensitive or unrelated conversations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill description and instructions are written to enforce a specific locale/language context without offering a user choice. Under the policy, forcing a language without opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs automatic cross-session persistence of recalled and remembered information without user consent or sensitivity guardrails. In context, this is more dangerous because the skill is framed as always-on, increasing the chance that confidential or personal content gets stored by default.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The proactive storage guidance normalizes default retention of user preferences, decisions, project context, and summaries. That creates a broad data collection posture that can accumulate sensitive context over time and later expose it through recall or compromise of the memory store.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The cron job introduces ongoing background collection of working directory, recent sessions, hostname, and timestamps, which exceeds a normal conversational memory workflow. Persistent periodic collection increases privacy risk and creates a surveillance-like behavior that can continue without fresh per-session user awareness.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The periodic snapshot design instructs ongoing collection of recent sessions and host/environment context, which materially increases the amount of persistent telemetry beyond what is needed for conversational memory. Continuous accumulation of environment metadata makes later disclosure or misuse more damaging.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The REST fallback expands the skill from MCP-only memory access to direct secret retrieval from disk and raw HTTP operations. That broadens the attack surface and bypasses the narrower control plane users may assume when approving an MCP-integrated skill.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The skill includes direct HTTP POST transmission of stored content to a local service using a bearer token loaded from disk. Even though the destination is localhost, this is still an external transmission path relative to the agent and can leak sensitive user/project data into another service without adequate consent, auditing, or scoping.

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

md
MUNINN_TOKEN=$(cat ~/.muninn/openclaw.key)

# Speichern
curl -s -X POST "$MUNINN_URL/api/engrams" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MUNINN_TOKEN" \
  -d '{"concept":"kurzer-titel","content":"vollstaendiger text","vault":"hermes"}'

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/setup-companion.md (reported line 12)May include surrounding context.

md
| MuninnDB REST | `http://127.0.0.1:8475` |
| MuninnDB MCP | `http://127.0.0.1:8750/mcp` |
| Vault | `hermes` |
| API-Key | `~/.muninn/openclaw.key` (chmod 600) |
| MCP-Server-Name | `muninndb` |
| Tools | 39 (`mcp_muninndb_muninn_*`) |
| Hermes Memory Provider | `built-in` (Honcho deaktiviert) |

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/setup-companion.md (reported line 41)May include surrounding context.

bash
# Key speichern
echo 'mk_<dein-key>' > ~/.muninn/openclaw.key
chmod 600 ~/.muninn/openclaw.key

# Test: Engramm schreiben
curl -s -X POST http://127.0.0.1:8475/api/engrams \

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/setup-companion.md (reported line 44)May include surrounding context.

md
chmod 600 ~/.muninn/openclaw.key

# Test: Engramm schreiben
curl -s -X POST http://127.0.0.1:8475/api/engrams \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $(cat ~/.muninn/openclaw.key)" \
  -d '{"concept":"test","content":"Integration funktioniert","vault":"hermes"}'

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The setup guide adds a cron-based snapshot feature that goes beyond the stated purpose of automatic MCP-backed memory loading. It instructs periodic collection of host and recent session context and stores it in MuninnDB, which creates an unexpected data collection channel and persistence behavior users may not anticipate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The cron instructions automate collection of the current working directory and recent Hermes sessions, then upload that context to MuninnDB without any privacy notice, consent step, or warning about possible sensitive contents. Even though the endpoint is localhost, this still persists potentially sensitive local context into another service and expands exposure if that service is later queried or compromised.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The cron snapshot script explicitly gathers recent session data and working-directory context and writes it into persistent memory. That behavior can capture sensitive prompts, project names, filesystem locations, or operational metadata and retain them beyond the active session.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This POST sends automatically collected snapshot content, including host and session context, into MuninnDB on a recurring basis. While the destination is localhost, the dangerous part is the persistent transfer of potentially sensitive context into another system without clear consent or minimization.

Content

Scanner excerpt · references/setup-companion.md (reported line 82)May include surrounding context.

md
Letzte Sessions: $RECENT_SESSIONS"

# Speichern
curl -s -X POST "$MUNINN_URL/api/engrams" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MUNINN_TOKEN" \
  -d "$(jq -n --arg c "cron-snapshot-$HOSTNAME" --arg x "$SUMMARY" \

Session Persistence

Medium
Category
Rogue Agent
Confidence
93% confidence
Finding

The cron job establishes persistent, recurring execution that continuously captures and stores context every 30 minutes. Persistence increases risk because collection continues beyond the immediate setup session, making accidental long-term retention of sensitive metadata more likely.

Content

Scanner excerpt · references/setup-companion.md (reported line 92)May include surrounding context.

Cron-Job erstellen

bash
cronjob action=create \
  name="MuninnDB Memory Snapshot" \
  schedule="every 30m" \
  script=muninndb-memory-snapshot.sh \

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · scripts/muninndb-memory-snapshot.sh (reported line 9)May include surrounding context.

sh
# Vault: hermes
# Silent bei Erfolg, Error-Output bei Fehlschlag
# ==========================================
# Installiert via: cronjob action=create \
#   name="MuninnDB Memory Snapshot" \
#   schedule="every 30m" \
#   script=muninndb-memory-snapshot.sh \

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The script reads a bearer token from ~/.muninn/openclaw.key and uses it for authenticated requests without any user-facing indication. Silent use of local credentials in an automatically scheduled task increases the risk of undisclosed privilege use and can normalize hidden authenticated data flows.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The script periodically captures host context, current working directory, and recent Hermes session metadata, then persists that data into MuninnDB. That exceeds the narrowly described 'auto-load memory layer' purpose and creates a stealthy data collection channel that can reveal sensitive project names, filesystem paths, and user activity patterns.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Collecting pwd output and recent session listings is privacy-sensitive because those values may contain repository names, customer identifiers, task history, or other operational context unrelated to the advertised function. In a background cron job, this occurs automatically and silently, increasing the risk of unnoticed retention of sensitive metadata.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script silently transmits local working-directory and session metadata to an HTTP API without notifying the user at runtime. Even though the destination is localhost, this is still external transmission to another service boundary and may expose sensitive data to any process with access to that service or its storage.

Content

No source excerpt is available for this finding.