ClawHub
Back to skill

Security audit

Pitch Deck V2

Security checks for vulnerabilities and agentic risk

Overview

This skill appears purpose-aligned, but users should avoid submitting confidential pitch materials unless they accept third-party API processing and temporary hosted PPTX links.

Install only if you are comfortable sending the startup information you provide to the third-party API and receiving PPTX files through a temporary hosted link. Do not submit confidential, regulated, or investor-sensitive material without confirming the provider's privacy, retention, access-control, and deletion practices.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to submit detailed startup information and optional identifying fields such as userId and session metadata to a third-party API, but it does not disclose how that data is transmitted, stored, retained, or shared. Because pitch deck inputs can contain confidential business strategy, traction, fundraising, and team information, the omission creates a real privacy and confidentiality risk rather than a purely informational issue.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The PPTX workflow returns a remote download URL and states the file remains available for 7 days, which implies generated presentation content is stored server-side. The skill does not warn users that sensitive pitch materials may persist on external infrastructure and be retrievable through a link, increasing the risk of unauthorized access, leakage, or unintended sharing.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

This finding reflects actual external transmission and hosting of generated output at a third-party domain. In this skill's context, external transmission is expected for API use, but it is still security-relevant because the transmitted content may include commercially sensitive startup information and the returned file link may expose that content outside the user's local environment.

Content

Scanner excerpt · SKILL.md (reported line 98)May include surrounding context.

md
"status": "success",
  "filename": "TechVenture_AI_Pitch_Deck_20240115.pptx",
  "fileSize": "2.4 MB",
  "downloadUrl": "https://api.mkkpro.com/files/temp/pptx_abc123xyz.pptx",
  "expiresIn": "7 days",
  "generatedAt": "2024-01-15T10:31:30Z"
}

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 224)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/creative/pitch-deck-v2
- **API Docs:** https://api.mkkpro.com:8077/docs

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest describes the skill as a 'professional pitch deck outline generator,' which implies producing structured outline content rather than full presentation artifacts. The OpenAPI spec adds a separate /api/pitchdeck/generate-pptx endpoint explicitly described as generating an actual PowerPoint presentation file, which expands the behavior beyond the stated outline-only scope.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The API accepts sessionId, userId, and timestamp fields but provides no privacy notice, minimization guidance, or indication of how these identifiers are transmitted, stored, or protected. This creates risk of unnecessary collection or leakage of user-linked metadata, especially if callers send stable identifiers that can be correlated across requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This JSON manifest exposes skill functionality through generic descriptions like "Generate Pitch Deck" and "Generate comprehensive pitch deck outline" but provides no explicit trigger phrases, scope limits, or exclusion conditions. For a manifest file, the lack of specificity can make invocation criteria ambiguous compared with a narrowly defined command or context.

Content

No source excerpt is available for this finding.