ClawHub
Back to skill

Security audit

Kiri Engine Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed KIRI Engine helper that uploads user-selected media for 3D reconstruction, with manageable risks around plaintext API key storage and third-party file processing.

Before installing, make sure you are comfortable storing a KIRI API key in a local plaintext config file and sending the selected photos or videos to KIRI Engine for processing. Keep the key file private, rotate the key if exposed, avoid uploading sensitive media unless approved, and choose the download directory carefully because extracted files may overwrite existing names there.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (10)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · tests/test-image-filter.ps1 (reported line 38)May include surrounding context.

text
$root = Join-Path ([IO.Path]::GetTempPath()) ("kiri-filter-" + [guid]::NewGuid().ToString('N'))
New-Item -ItemType Directory -Path (Join-Path $root 'sub') -Force | Out-Null
foreach ($n in 'a.jpg','b.JPG','c.jpeg','d.png','e.tif','f.tiff') { Set-Content (Join-Path $root $n) 'x' }
foreach ($n in 'notes.txt','model.obj','secret.json','clip.mp4') { Set-Content (Join-Path $root $n) 'x' }
Set-Content (Join-Path $root 'sub\g.png') 'x'
Set-Content (Join-Path $root 'sub\readme.md') 'x'

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · tests/test-image-filter.ps1 (reported line 47)May include surrounding context.

text
$root = Join-Path ([IO.Path]::GetTempPath()) ("kiri-filter-" + [guid]::NewGuid().ToString('N'))
New-Item -ItemType Directory -Path (Join-Path $root 'sub') -Force | Out-Null
foreach ($n in 'a.jpg','b.JPG','c.jpeg','d.png','e.tif','f.tiff') { Set-Content (Join-Path $root $n) 'x' }
foreach ($n in 'notes.txt','model.obj','secret.json','clip.mp4') { Set-Content (Join-Path $root $n) 'x' }
Set-Content (Join-Path $root 'sub\g.png') 'x'
Set-Content (Join-Path $root 'sub\readme.md') 'x'

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · tests/test-image-filter.ps1 (reported line 58)May include surrounding context.

text
$root = Join-Path ([IO.Path]::GetTempPath()) ("kiri-filter-" + [guid]::NewGuid().ToString('N'))
New-Item -ItemType Directory -Path (Join-Path $root 'sub') -Force | Out-Null
foreach ($n in 'a.jpg','b.JPG','c.jpeg','d.png','e.tif','f.tiff') { Set-Content (Join-Path $root $n) 'x' }
foreach ($n in 'notes.txt','model.obj','secret.json','clip.mp4') { Set-Content (Join-Path $root $n) 'x' }
Set-Content (Join-Path $root 'sub\g.png') 'x'
Set-Content (Join-Path $root 'sub\readme.md') 'x'

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · tests/test-image-filter.ps1 (reported line 60)May include surrounding context.

text
$root = Join-Path ([IO.Path]::GetTempPath()) ("kiri-filter-" + [guid]::NewGuid().ToString('N'))
New-Item -ItemType Directory -Path (Join-Path $root 'sub') -Force | Out-Null
foreach ($n in 'a.jpg','b.JPG','c.jpeg','d.png','e.tif','f.tiff') { Set-Content (Join-Path $root $n) 'x' }
foreach ($n in 'notes.txt','model.obj','secret.json','clip.mp4') { Set-Content (Join-Path $root $n) 'x' }
Set-Content (Join-Path $root 'sub\g.png') 'x'
Set-Content (Join-Path $root 'sub\readme.md') 'x'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The README explicitly instructs users to store the API key in a plaintext JSON file under the user profile. Plaintext credential storage increases the chance of accidental disclosure through local compromise, backups, sync tools, shared accounts, or malware, and the documentation does not prominently warn users about that risk or suggest safer storage options.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README directs users to upload local videos and image sets to a remote third-party API as part of the normal workflow, but it does not clearly warn that potentially sensitive local media will be transmitted off-device. This can lead users to upload confidential, personal, or regulated content without understanding the privacy, retention, or data-handling implications.

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 · README.md (reported line 131)May include surrounding context.

md
)

$ConfigPath = Join-Path $env:USERPROFILE '.kiri-engine-config.json'
$BaseUrl = 'https://api.kiriengine.app/api/v1/open'

# ── 读取 API Key ──────────────────────────────────────────
function Get-ApiKey {

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 178)May include surrounding context.

md
)

$ConfigPath = Join-Path $env:USERPROFILE '.kiri-engine-config.json'
$BaseUrl = 'https://api.kiriengine.app/api/v1/open'

# ── 读取 API Key ──────────────────────────────────────────
function Get-ApiKey {

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 · scripts/kiri-engine.ps1 (reported line 50)May include surrounding context.

text
)

$ConfigPath = Join-Path $env:USERPROFILE '.kiri-engine-config.json'
$BaseUrl = 'https://api.kiriengine.app/api/v1/open'

# ── 读取 API Key ──────────────────────────────────────────
function Get-ApiKey {

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language instructions are presented in Chinese throughout the README, which can effectively force a specific language for users who do not read it. The file does not indicate that Chinese is optional, provide an alternate language, or justify a locale-specific constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.