ClawHub
Back to skill

Security audit

企业文件批量脱敏

Security checks for vulnerabilities and agentic risk

Overview

The skill’s document uploads, optional OCR, and manual review requirements fit its disclosed document-redaction purpose.

This is a cloud service: original documents leave your computer. Confirm that its privacy and retention terms suit your files, protect the stored API key, and review every page before sharing results. OCR and generation require separate fee approval; redaction does not guarantee every secret was found.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied commands perform platform configuration and service management, not document processing, sensitive-region confirmation, or reviewed-copy generation. Although API configuration could support a larger workflow, this chunk provides no connection to the declared purpose and consists entirely of configuration changes and a gateway restart.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/HTTP-REQUESTS.md (reported line 12)May include surrounding context.

BASE="${BASE%/}" : "${DOCUMENT_REDACTION_API_KEY:-${AI_SKILLS_API_KEY:?请先配置平台 Key}}"

CREATE_KEY 为本次创建意图生成并保存的 UUID；重试沿用它。

curl -sS -X POST "$BASE/api/v1/document-redaction/projects"
-H "Authorization: Bearer ${DOCUMENT_REDACTION_API_KEY:-${AI_SKILLS_API_KEY}}"
-H "Idempotency-Key: $CREATE_KEY" -H 'Content-Type: application/json' -d '{}'

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/HTTP-REQUESTS.md (reported line 46)May include surrounding context.

按 OPERATIONS 中的实际字段生成私有 request.json，每项独立生成并保存稳定 UUID OPERATION_KEY：

sh
curl -sS -X POST "$BASE/api/v1/document-redaction/$OPERATION" \
  -H "Authorization: Bearer ${DOCUMENT_REDACTION_API_KEY:-${AI_SKILLS_API_KEY}}" \
  -H "Idempotency-Key: $OPERATION_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json