Back to skill

Security audit

Customer Education

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly fits its stated course-building purpose, but its update flow can make the agent run command text supplied by the PersonWise CLI/service after broad approval.

Review this skill before installing. It is not clearly malicious, but you should only approve installs or updates when the shown command is a known PersonWise bootstrap or upgrade command from the installed skill directory, and avoid approving arbitrary shell text returned by the service or CLI.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:112
Finding

Execution of Server-Controlled Update Commands

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly directs the agent to perform CLI installation, update, and authentication setup 'quietly' while minimizing normal user-facing disclosure. Because these actions can modify the local environment and trigger OAuth flows, suppressing clear notice and confirmation increases the risk of non-transparent tool execution and reduces the user's ability to make informed security decisions. In this context, the skill does include some safety constraints (official CLI only, no alternate origins, host-enforced approval), which lowers severity, but the stealth-oriented phrasing still creates a real transparency and consent vulnerability.

Content

No source excerpt is available for this finding.

Scope Creep

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest lists only "Bash" permissions, but this script fetches a release artifact from releases.personwise.ai using curl. Network access is a distinct capability beyond local shell execution, so the implemented behavior exceeds the declared permission scope.

Content

No source excerpt is available for this finding.

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"