Back to skill

Security audit

Addiction Self Assessment

Security checks for vulnerabilities and agentic risk

Overview

The skill’s addiction self-assessment content is coherent, but it requests unexplained filesystem access and defines sensitive substance-use state with reminders without privacy or retention controls.

Review this before installing if you are uncomfortable granting filesystem access to a health-related skill. Prefer a pinned or otherwise verified installer, avoid broad filesystem permission unless the runtime constrains it, and keep substance-use screening data session-only unless you explicitly opt into reminders or stored tracking with clear deletion controls.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (3)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:15
Finding

Unpinned Package Execution Through npx

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:11
Finding

Unnecessary Filesystem Capability Violates Least Privilege

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:341
Finding

Sensitive Health State and Scheduled Follow-Up Lack Privacy Controls

Content
View full analysis
= 2 AND actions_taken.resources_provided IS false" action: "Your CAGE score suggests this warrants a closer look. This isn't a label — it's a signal. Would you like to go through the more detailed AUDIT screening, or would you prefer to look at treatment and support options?" - name: tracking ...[truncated 3020 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 190)May include surrounding context.

md
**Agent action**: Deliver harm reduction information without moral commentary. Reducing risk is always better than pretending abstinence is the only option.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 325)May include surrounding context.

md
## Rules

- Never moralize. The user knows substance use carries risk. Judgment is not information.
- Never diagnose. These are screening tools, not diagnoses. Only a clinician can diagnose a substance use disorder.
- Always flag medically dangerous withdrawal (alcohol and benzodiazepines) clearly and urgently.
- Present Medication-Assisted Treatment as legitimate, evidence-based medicine, not as "replacing one addiction with another."

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 334)May include surrounding context.

md
## Tips

- Tracking your use honestly for two weeks will tell you more than any screening tool. Write down every drink, every use, every day. Don't judge it — just record it. The pattern will speak for itself.
- If you're questioning your use, that itself is data. People without a problem rarely spend time wondering if they have one.
- Recovery is not linear. Relapse is not failure — it's information about what needs to change in your approach. Most people who eventually achieve long-term recovery had multiple attempts.
- MAT (medication-assisted treatment) has the strongest evidence base for opioid use disorder. If a treatment program tells you medication is a "crutch," find a different program.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The install instruction invokes npx clawhub without a pinned version, which can fetch and execute whatever package version is current at install time. This creates a supply-chain risk: a compromised publisher account, malicious update, or breaking change could execute untrusted code on the installer’s system.

Content

No source excerpt is available for this finding.