ClawHub
Back to skill

Security audit

localization-push

Security checks for vulnerabilities and agentic risk

Overview

The localization workflow fits its purpose, but its optional automation can apply store-listing changes before human review despite promising approval first.

Use the interactive workflow and approve each diff. Before enabling unattended runs, enforce mandatory human approval in AppGoat or stop automation after proposals. Pin the downloaded playbooks to a reviewed commit. The supplied static scan reported no findings, but the approval inconsistency is directly supported by the artifacts.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

The unattended workflow calls apply_action before user approval despite claiming that nothing is written until dashboard approval.

High
Category
Excessive Agency
Confidence
96% confidence
Finding

The unattended workflow instructs the agent to call apply_action without the user's review, although the main procedure treats that call as the write operation and describes pending approval as only one possible outcome. Nothing shown enforces dashboard approval for every action, so a connection permitting immediate application could publish unreviewed metadata changes despite the workflow's assurance that nothing is written before approval.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 157)May include surrounding context.

md
cp -r /tmp/appgoat-skills/skills/* .claude/skills/
          # Hosted AppGoat MCP server; the key goes into a file, not the command line.
          jq -n --arg key "$APPGOAT_API_KEY" \
            '{mcpServers: {appgoat: {type: "http", url: "https://api.appgoat.ai/mcp", headers: {"x-api-key": $key}}}}' \
            > "$RUNNER_TEMP/appgoat-mcp.json"
      - uses: anthropics/claude-code-action@v1
        with:

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · reference/api.md (reported line 23)May include surrounding context.

bash
CON=con_… APP=1234567890
curl -s -G -H "x-api-key: $APPGOAT_API_KEY" "https://api.appgoat.ai/v1/connections/$CON/listings" \
  -d app=$APP -d locale=de-DE | jq '.data | {fields, editable, notes}'

curl -s -H "x-api-key: $APPGOAT_API_KEY" -H "content-type: application/json" https://api.appgoat.ai/v1/actions \

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · reference/api.md (reported line 26)May include surrounding context.

md
curl -s -G -H "x-api-key: $APPGOAT_API_KEY" "https://api.appgoat.ai/v1/connections/$CON/listings" \
  -d app=$APP -d locale=de-DE | jq '.data | {fields, editable, notes}'

curl -s -H "x-api-key: $APPGOAT_API_KEY" -H "content-type: application/json" https://api.appgoat.ai/v1/actions \
  -d '{"type":"keywords.set","connection":"'$CON'","dry_run":true,"source":"playbook:localization-push",
       "params":{"app":"'$APP'","locale":"de-DE","mode":"replace","keywords":"gewohnheit,routine,ziel"}}' \
  | jq '.data | {id, diff, guardrail}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · reference/api.md (reported line 3)May include surrounding context.

md
# REST fallback

Without the AppGoat MCP server, call the API directly. Base URL `https://api.appgoat.ai/v1`,
header `x-api-key: $APPGOAT_API_KEY` (create a key at https://dash.appgoat.ai). Responses are
`{ "data": …, "meta": { "credits_used", "credits_remaining", … } }`; errors are
`{ "error": { "code", "message", "hint", "approve_url"? } }` - read `hint`.

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 · reference/api.md (reported line 23)May include surrounding context.

bash
CON=con_… APP=1234567890
curl -s -G -H "x-api-key: $APPGOAT_API_KEY" "https://api.appgoat.ai/v1/connections/$CON/listings" \
  -d app=$APP -d locale=de-DE | jq '.data | {fields, editable, notes}'

curl -s -H "x-api-key: $APPGOAT_API_KEY" -H "content-type: application/json" https://api.appgoat.ai/v1/actions \

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 · reference/api.md (reported line 26)May include surrounding context.

md
curl -s -G -H "x-api-key: $APPGOAT_API_KEY" "https://api.appgoat.ai/v1/connections/$CON/listings" \
  -d app=$APP -d locale=de-DE | jq '.data | {fields, editable, notes}'

curl -s -H "x-api-key: $APPGOAT_API_KEY" -H "content-type: application/json" https://api.appgoat.ai/v1/actions \
  -d '{"type":"keywords.set","connection":"'$CON'","dry_run":true,"source":"playbook:localization-push",
       "params":{"app":"'$APP'","locale":"de-DE","mode":"replace","keywords":"gewohnheit,routine,ziel"}}' \
  | jq '.data | {id, diff, guardrail}'

Static analysis

No suspicious patterns detected.