Back to skill

Security audit

TOSR Test Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed temporary integration-test skill with no bundled code, but it should only be used in a controlled test context because it describes real ClawHub API create/update/delete operations.

Install or invoke this only if you intend to run ClawHub skill lifecycle tests. Confirm it targets the fixed test slug in a test account or sandbox before allowing publish, update, or delete operations against the real API.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
93% confidence
Finding

The skill explicitly includes a DELETE operation on /api/v1/skills/{slug}, which is a destructive API capability that could be abused if parameters are attacker-controlled or insufficiently validated. In the context of a real API lifecycle test, this is more dangerous because it targets live resources and could delete unintended skills if slug selection or authorization boundaries fail.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

md
1. **Publish** — Creates a new skill via POST /api/v1/skills with multipart form data
2. **Inspect** — Retrieves skill metadata via GET /api/v1/skills/{slug}
3. **Update** — Publishes a new version of an existing skill
4. **Delete** — Removes the skill via DELETE /api/v1/skills/{slug}

## Notes

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description field is written in Chinese while the rest of the skill documentation is in English, indicating a language-specific default without any user choice or opt-in. The policy explicitly flags locale or language constraints when the skill does not offer a user-selectable language option or justify the restriction.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
88% confidence
Finding

The skill describes automatically deleting a skill after test completion, which is an autonomous state-changing action against a real external API. Even though framed as test cleanup, autonomous deletion without explicit runtime confirmation or strict scope checks can cause unintended destructive actions if the slug, environment, or target is mis-scoped.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
## Notes

This skill is ephemeral and will be automatically deleted after the test completes.
If you see this skill listed on clawhub, it means a test run failed to clean up properly.