Back to skill

Security audit

PKU Info Common

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only guide for a PKU authentication helper crate; it handles sensitive auth concepts but its behavior is disclosed and purpose-aligned.

Install this if you work on the PKU info-common authentication crate or related PKU CLI tools. Be aware that it documents credential, keyring, session, cookie, and SMS-code handling, so use it only in that intended context and avoid setting PKU_PASSWORD or PKU_SMS_CODE in broad shell environments.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The activation guidance is overly broad and includes generic triggers like shared auth concepts, OTP, session persistence, keyring, credentials, and QR code display, which can cause the skill to be invoked in contexts beyond the intended crate. Over-triggering a security-sensitive authentication skill increases the chance that an agent will apply credential-handling or auth-specific procedures in unrelated tasks, expanding exposure to secrets and causing inappropriate behavior.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

md
- Windows: Windows Credential Manager
- **Environment variables**: `PKU_USERNAME`, `PKU_PASSWORD`, `PKU_SMS_CODE`
- **SMS code resolution**: `resolve_sms_code()` — env var `PKU_SMS_CODE` → interactive
- **SMS auto-confirm**: `confirm_send_sms()` — auto-confirms when `PKU_SMS_CODE` is set
- **Keyring management**: `keyring_store()`, `keyring_clear()`, `keyring_has_credential()`
- **Session check**: `check_session(app_name)` — returns Valid / Expired / NotFound
- Passwords **never** written to disk — keyring is OS-encrypted, env vars are in-memory only

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

The instruction "All user-facing strings in Chinese" imposes a fixed language choice as a blanket policy. This is a natural-language locale policy constraint with no indication of user choice, opt-in, or a documented region-specific justification.

Content

No source excerpt is available for this finding.