Back to skill

Security audit

Customer Onboarding Course

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its stated PersonWise course-building purpose, but its update path gives too much trust to server-provided command text and unsigned native installer flows.

Review this before installing. Only proceed if you trust PersonWise and are comfortable with a local CLI install, browser OAuth, course-credit use, and uploads of selected onboarding materials. Treat any proposed update command as sensitive: decline anything that is not clearly an official PersonWise install or update action.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:109
Finding

Execution of Server-Supplied Update Commands

Content
View full analysis
` with the directory of this installed Skill (the directory containing this Skill's SKILL.md). Never run `doctor` or a generic capability preflight to check freshness; the `update check` command above is the freshness check. Never ask more than once per component per session, and never substitute another command, flag, origin, or download path for the printed `action`. ``` ### Technical Analysis The Skill treats an `action` command returned by the remote PersonWise service as executable instructions. It requires user approval, but it does not require the Agent to validate the returned command against a locally defined grammar or allowlist before execution. Approval is not an adequate command-integrity boundary. A user may reasonably assume that the displayed command is a routine PersonWise update, while a compromised or malfunctioning service could return shell operators, an unexpected executable, unsafe arguments, or a command targeting unrelated local resources. This creates a command-injection trust boundary in which remote response data can become local code execution. The instructio ...[truncated 1587 chars]
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
assets/bootstrap.ps1:10
Finding

Native Publisher Signature Verification Is Disabled for Downloaded Executables

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · assets/bootstrap.sh (reported line 165)May include surrounding context.

sh
echo "Release executable checksum mismatch." >&2
  exit 6
fi
chmod 700 "$candidate"
if [ "$(uname -s)" = "Darwin" ] && [ "$native_signature_status" = "verified" ]; then
  codesign --verify --deep --strict --verbose=2 "$candidate"
  spctl --assess --type execute --verbose=2 "$candidate"