ClawHub
Back to skill

Security audit

Source Scout

Security checks for vulnerabilities and agentic risk

Overview

Source Scout is a transparent research-assistance skill that searches the web, cites sources, and may attach sourced images; its network and file behavior is disclosed and fits its purpose.

Install this if you want factual answers to routinely use web search and citations. Be aware that factual prompts may send search terms to external services, and image-enhanced answers may download a sourced image into the local workspace before attaching it.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger criteria are broad enough to match many ordinary factual prompts, including common 'what/who/why/how' questions, and the description says to trigger even when the user did not ask for sources. This increases the chance of unintended invocation of a capability that performs external searches and may download files, expanding tool usage beyond user expectation and increasing exposure to privacy, cost, and untrusted-content risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs the agent to perform web searches and to download remote images to local storage, but it does not require user consent or a user-visible notice before network access and file writes occur. In agent runtimes where tool use is sensitive, this can lead to unintended outbound requests, privacy leakage through queried terms, and unanticipated local artifact creation from untrusted remote content.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

Line L38 describes downloading images locally before attaching them, which implies external network retrieval and local file creation. The README does not explicitly warn users that the skill may save downloaded media to the local environment as part of its workflow.

Content

No source excerpt is available for this finding.