Back to skill

Security audit

Lead Magnet

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for creating PersonWise lead-magnet courses, but its update path grants a remote response too much authority to prescribe shell commands.

Review this before installing. It appears designed for PersonWise course creation, not theft or destruction, but only approve installer or update commands that clearly invoke the expected PersonWise bootstrap or CLI from expected locations and origins. A safer release should validate update actions locally and require current signed trust metadata and native publisher verification where available.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
assets/bootstrap.sh:68
Finding

Platform-Native Signature Verification Is Disabled for Downloaded Executables

Content
View full analysis
&2 exit 9 fi ``` ```sh if [ "$(uname -s)" = "Darwin" ] && [ "$native_signature_status" = "verified" ]; then codesign --verify --deep --strict --verbose=2 "$candidate" spctl --assess --type execute --verbose=2 "$candidate" actual_identity="$(codesign -dv --verbose=4 "$candidate" 2>&1 | sed -n 's/^Authority=//p' | head -1)" if [ -z "$native_identity" ] || [ "$actual_identity" != "$native_identity" ]; then echo "Apple signing identity mismatch." >&2 exit 6 fi fi ``` Windows bootstrap: ```powershell $nativeSignatureRequired = $false if ($nativeSignatureRequired -and "deferred-founder-approved" -ne "verified") { [Console]::Error.WriteLine('{"schema_version":"1","ok":false,"error":{"code":"NATIVE_SIGNATURE_REQUIRED","message":"This release candidate has not completed Authenticode signing.","retryable":false,"action":"use_verified_release"},"request_id":"bootstrap-local"}') exit 9 } ``` ```powershell if ("deferred-founder-approved" -eq "verified") { $signature = Get-AuthenticodeSignature -LiteralPath $candidate if ($signature.Status -ne "Valid" -or $signature.SignerCertificate.Thumbprint -ne "") { throw "Authenticode verification failed" } ...[truncated 2353 chars]
Remediation
View remediation

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:111
Finding

Remote Service Responses Can Prescribe Shell Commands for Agent Execution

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 directs the Agent to execute the exact `action` command printed by the PersonWise CLI or remote service after obtaining general update approval. The documented procedure does not require the Agent to: - Parse the response as structured command metadata. - Restrict the executa ...[truncated 2341 chars]
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

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"

Vague Triggers

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This JSON manifest-like file contains endpoint and signature metadata but provides no information about when the skill should activate or what user phrases should invoke it. For manifest files, missing specificity on trigger scope or constraints can lead to ambiguous or overly broad invocation behavior if other tooling relies on this descriptor without separate trigger definitions.

Content

No source excerpt is available for this finding.