ClawHub
Back to skill

Security audit

Presently

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward external API wrapper for turning supplied text into presentation slides, with no local code execution or persistence.

Install only if you are comfortable sending the source text and any provided identifiers to ToolWeb's external API. Avoid including secrets, credentials, regulated data, or unnecessary personal email addresses in presentation input.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation explicitly includes user_id and user_email as request fields and shows them in examples, but provides no privacy notice, minimization guidance, retention policy, or warning that this data is sent to a third-party service. In an agent skill context, this can lead users or integrators to transmit personally identifiable information without understanding where it goes or how it is handled.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The skill references and depends on an external endpoint (api.toolweb.in), meaning user-provided content and metadata will be transmitted outside the local trust boundary. External transmission is expected for an API skill, but it is still security-relevant here because the skill processes large free-form text and may also include identifiers or email addresses, increasing data exposure risk if users are not warned.

Content

Scanner excerpt · SKILL.md (reported line 186)May include surrounding context.

md
## References

- Kong Route: https://api.toolweb.in/tools/presently
- API Docs: https://api.toolweb.in:8174/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This is a manifest-style file, so vague trigger review applies. The operation is exposed only as a generic 'Create Presentation' action with no clarifying description of when it should or should not be used, which can lead to overly broad activation by agents or tooling that infer capability from OpenAPI metadata.

Content

No source excerpt is available for this finding.