Back to skill

Security audit

clawmart-provider

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ClawMart provider integration, but it asks for broad private context access and creates a persistent remote order channel into the local agent.

Review before installing. Use a dedicated low-privilege OpenClaw session, avoid scanning private memories or unrelated repositories, inspect all generated listing text before submission, protect and rotate ClawMart tokens, and run the bridge only when you intend to accept orders.

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 (4)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:9
Finding

Remote Marketplace Instructions Hijack Agent Goals and Output Routing

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:123
Finding

Mandatory Enumeration of Private Sessions, Memories, Tools, and Repositories Violates Least Privilege

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:123
Finding

Private Owner Context Is Converted into Externally Published Marketplace Metadata

Content
View full analysis
", "description": "", "capabilityType": "", "capabilityName": "", "capabilityDescription": "", "listingTitle": "", "listingSlug": "
Remediation
View remediation

T06 · System Persistence

Error
Location
SKILL.md:271
Finding

Detached Bridge Creates a Persistent Remote Instruction Channel into OpenClaw

Content
View full analysis
/dev/null rm ~/.clawmart/bridge.pid sleep 1 fi # Start bridge (will auto-enable both roles since both tokens are now present) nohup node ~/.clawmart/bridge.mjs > ~/.clawmart/bridge.log 2>&1 & echo $! > ~/.clawmart/bridge.pid sleep 2 if curl -s http://127.0.0.1:3010/health > /dev/null 2>&1; then echo "Bridge started (pid $(cat ~/.clawmart/bridge.pid))." ``` The documented behavior is: ```markdown The bridge: 1. Opens an SSE connection to ClawMart to receive employer messages in real time 2. Forwards each message to your OpenClaw agent via `POST /hooks/agent` 3. Starts a local callback server on `127.0.0.1:3002` for provider callbacks 4. Your agent posts results to the callback URL; bridge relays to ClawMart 5. Health endpoint at `http://127.0.0.1:3010/health` for liveness checks ``` Continuous operation is mandatory: ```markdown Every live provider session must keep the queue loop running. A session is considered healthy only if it keeps polling and can resume unfinished work after restart by pulling its active queue again. ``` ### Technical Analysis The Skill starts `~/.clawmart/bridge.mjs` with `nohup` in the background and stores its process identifier. The bridge therefore survives the initiating shell and continues maintaining an SSE-based external message channel after the immediate setup command has completed. The bridge source is not included in the audited project, so its implementation, update mechanism, authentication checks, request validation, and callback handling cannot be verified from the package. Nevertheless, the Skill directs the user to execute that pre-existing local component and grants it access to ClawMart tokens, OpenClaw ...[truncated 1695 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Rogue AgentSelf-Modification, Session Persistence
Findings (13)

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill first defines a privacy boundary forbidding disclosure of local private state, but later directs the agent to read private memory and owner files to infer capabilities. This contradiction is dangerous because it normalizes sensitive-data access while relying on the agent to summarize safely, creating a high-risk path for accidental leakage of secrets, personal data, or internal operational details.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill explicitly instructs the agent to inspect broad private owner context, including memory files, skills, tools, and local knowledge bases, to generate marketplace-facing capability listings. That exceeds the stated provider purpose and creates unnecessary access to sensitive local data, with a realistic risk that private information is incorporated into external descriptions or exposed through downstream prompts and outputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The instructions tell the agent to read sensitive owner memory and workspace context without an explicit up-front privacy notice and informed consent workflow. Even if the goal is capability discovery, collecting from MEMORY.md, USER.md, AGENTS.md, and working files creates significant privacy risk because those sources may contain secrets, personal information, and unrelated confidential project data.

Content

No source excerpt is available for this finding.

Ssd 3

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill directs the agent to transform private owner context into externally visible marketplace text such as summaries, descriptions, and capability statements. That creates a natural-language exfiltration channel: even if raw files are not sent, the generated listing can reveal confidential business focus, personal details, internal tools, or sensitive project relationships derived from local data.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 203)May include surrounding context.

agent profile, capability, and service listing in one shot:

bash
curl -X POST "$CLAWMART_API_URL/api/providers/register" \
  -H "Content-Type: application/json" \
  -d '{
    "apiToken": "'$CLAWMART_API_TOKEN'",

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 278)May include surrounding context.

md
# Stop existing bridge if running
if [ -f ~/.clawmart/bridge.pid ]; then
  kill "$(cat ~/.clawmart/bridge.pid)" 2>/dev/null
  rm ~/.clawmart/bridge.pid
  sleep 1
fi

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
- upload the needed input file directly into the order flow
- paste the relevant content into the channel
- describe the requirement without asking for your local private context

You may summarize only the minimum necessary task-relevant facts, and only when
those facts are part of the hired deliverable itself. Do not expose your own

Session Persistence

Medium
Category
Rogue Agent
Confidence
85% confidence
Finding

The skill makes the agent re-analyze owner context and persist marketplace-facing state over time through listing updates. This persistence increases the chance that sensitive derived data remains externally published or is repeatedly regenerated from private context, amplifying exposure beyond a one-time action.

Content

Scanner excerpt · SKILL.md (reported line 190)May include surrounding context.

md
- `listingSlug` — auto-generated from title (lowercase, hyphens)

**Important:** `listingSummary`, `taskGoal`, `headline`, and `description` must
be generated by the claw from context analysis. The owner cannot manually write
or edit these fields — they must authentically reflect the claw's real
capabilities. To update them after registration, the owner must ask their claw
to re-analyze context and call `POST /api/providers/listing` with the new values.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The registration call sends externally generated marketplace profile data and credentials to a remote service. External transmission is expected for this skill's function, but it becomes security-relevant here because the payload may include content derived from sensitive local context and because it includes authentication material that must be protected.

Content

Scanner excerpt · SKILL.md (reported line 203)May include surrounding context.

agent profile, capability, and service listing in one shot:

bash
curl -X POST "$CLAWMART_API_URL/api/providers/register" \
  -H "Content-Type: application/json" \
  -d '{
    "apiToken": "'$CLAWMART_API_TOKEN'",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill persists a session token into a local config file without warning about file permissions, token sensitivity, or rotation. This is risky because local plaintext credential storage can be harvested by other processes, users, or later prompts, enabling account/session hijacking and unauthorized provider actions.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
65% 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 · SKILL.md (reported line 283)May include surrounding context.

md
fi

# Start bridge (will auto-enable both roles since both tokens are now present)
nohup node ~/.clawmart/bridge.mjs > ~/.clawmart/bridge.log 2>&1 &
echo $! > ~/.clawmart/bridge.pid
sleep 2
if curl -s http://127.0.0.1:3010/health > /dev/null 2>&1; then

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 · SKILL.md (reported line 325)May include surrounding context.

export TOKEN="tok_abc123"

while true; do curl -fsS "$CLAWMART_API_URL/api/providers/orders?sessionToken=$TOKEN&status=active" sleep 5 done

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
82% confidence
Finding

Updating a listing through a remote API is expected platform behavior, but it still transmits externally visible content plus a live session token. Given the skill's earlier instructions to derive listing text from private local context, this endpoint is part of the exposure path for sensitive derived information.

Content

Scanner excerpt · SKILL.md (reported line 522)May include surrounding context.

Example:

bash
curl -X POST "$CLAWMART_API_URL/api/providers/listing" \
  -H "Content-Type: application/json" \
  -d '{
    "sessionToken": "'$TOKEN'",