Back to skill

Security audit

bossclaw

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent BossClaw profile-management purpose, but it asks agents to infer personal data from prior context and store a reusable API token in a predictable plaintext file.

Review before installing. Use it only if you are comfortable sending your BossClaw profile details to api-boss.dongyao.ren and with profile data such as email being public. Avoid letting it infer registration details from unrelated chat history or identity files, and do not keep the API token in a shared, synced, committed, or broadly readable workspace file.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:24
Finding

Overbroad Access to Conversation History and Local Identity Data

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:187
Finding

Reusable Authentication Token Stored in a Predictable Plaintext File

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The language adaptation section forces the skill to classify the conversation and default to Chinese unless recent messages indicate English, then requires all subsequent output to remain 100% in that language. This imposes a locale/language policy based on heuristic detection rather than offering the user an explicit language choice or opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill collects and transmits personal profile data including name, email, skills, personality, salary, and status to a remote third-party API, but does not require an explicit privacy notice or informed user consent at the point of transfer. This creates privacy and compliance risk because users may not understand what data is sent, where it is sent, and that some fields are publicly exposed.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs persisting an authentication token to bossclaw/token.md in plaintext and reusing it for later API calls. Storing long-lived credentials on disk without encryption, scope limits, rotation guidance, or secure storage controls increases the risk of credential theft from the workspace, logs, backups, or other tools with file access.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

The skill contains concrete instructions and examples for sending authentication tokens and user profile data to an external domain via API calls. External transmission is expected for this skill's function, but it remains security-relevant because it moves sensitive credentials and personal data off-platform to a third-party service, amplifying the impact of phishing, endpoint compromise, or unauthorized use.

Content

Scanner excerpt · SKILL.md (reported line 315)May include surrounding context.

md
---

## 🔗 真实接口参考(curl 验证)

bash
# 📊 查询简历(含 views 字段)