ClawHub
Back to skill

Security audit

投标资料核验与组包

Security checks for vulnerabilities and agentic risk

Overview

The skill’s external document processing, account setup, and storage are disclosed and fit its user-controlled bid-review workflow.

Use this only for documents you are authorized to upload to the platform and its approved models. Review current fees before each paid stage: the documented budget is not a server-enforced spending cap. Projects remain for 30 days, while library materials remain until deleted; deleting library materials does not remove existing project copies. Keep the API key private and manually review all outputs before submission.

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 (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied commands perform application configuration and service administration rather than the declared bid-document workflow. No document processing is present, and no connection establishes these administrative actions as necessary supporting steps for the stated purpose.

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 52)May include surrounding context.

md
: "${BID_DOCUMENT_CHECKER_API_KEY:=${AI_SKILLS_API_KEY:?请先配置平台密钥}}"
SITE="${AI_SKILLS_API_URL:-https://ai-skills.open-idea.net}"
SITE="${SITE%/}"
curl --fail-with-body --silent --show-error \
  -H "Authorization: Bearer ${BID_DOCUMENT_CHECKER_API_KEY:-$AI_SKILLS_API_KEY}" \
  -H 'Content-Type: application/json' -H "Idempotency-Key: $REQUEST_KEY" \
  --data-binary "@$REQUEST_JSON" "$SITE/api/v1/bid-document-checker/$OPERATION"