Back to skill

Security audit

Content Repurposing

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its PersonWise course-creation purpose, but its update flow asks the agent to run a returned command too broadly.

Review any PersonWise update command before approving it. The normal course workflow is scoped and mostly well controlled, but installation and updates can change a local executable or the installed skill, so only proceed if you trust the PersonWise update channel and the exact command shown.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:108
Finding

Unvalidated Update Action Can Be Executed as a Shell Command

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 instructs the Agent to execute an `action` command returned by the PersonWise CLI or its remote service. The command is treated as executable shell syntax rather than as structured data from which a trusted local command is constructed. No validation requirements are defined for the executable path, subcommand, arguments, update version, destination, or shell metacharacters. In particular, the instru ...[truncated 2587 chars]
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Scope Creep

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest lists only a Bash permission, but this PowerShell bootstrap script creates an HTTP client and downloads a release artifact from releases.personwise.ai. Network access is a broader capability than the declared permission baseline, so the code exceeds the manifest's stated permissions.

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"