Back to skill

Security audit

Security Awareness Training

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its course-building purpose, but its updater can run service-provided commands and install native executables, so it needs careful review before use.

Install only if you trust PersonWise's release and update service. Before approving any update, read the exact command the agent plans to run and decline anything that is not a clear PersonWise CLI or skill update. Also expect the skill to use browser OAuth, upload the documents you select, consume existing course credits, and publish or share a course only when requested.

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)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:107
Finding

Execution of Update Commands Supplied by a Remote Service

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 remote PersonWise update service. The response is treated as executable command content rather than parsed as structured data and converted into a command using a fixed local template. User approval provides an interaction boundary, but it does not validate the command. A compromised service, compromised API account, or malicious response could present an attacker-c ...[truncated 1707 chars]
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
assets/bootstrap.sh:52
Finding

Native Publisher-Signature Verification Is Disabled for Downloaded Executables

Content
View full analysis
&2 exit 9 fi ``` The downloaded executable is installed based primarily on embedded hashes: ```sh curl --disable --fail --silent --show-error --proto '=https' --tlsv1.2 \ --connect-timeout 10 --max-time 300 --max-filesize "26214400" \ --output "$archive" "$url" actual_sha256="$(sha256_file "$archive")" if [ "$actual_sha256" != "$expected_sha256" ]; then echo "Downloaded artifact checksum mismatch." >&2 exit 6 fi if [ "$(sha256_file "$candidate")" ...[truncated 4075 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 script performs an outbound download and installation path even though the skill metadata declares only Bash permission, creating a capability mismatch between what reviewers/users may expect and what the skill can do. Although the download is constrained with HTTPS, fixed size, and SHA-256 verification, it still installs executable code from the network, so the undeclared side effect materially increases supply-chain and consent risk.

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"