Back to skill

Security audit

Cart Recovery

Security checks for vulnerabilities and agentic risk

Overview

The skill is strategy-only and does not run code, but it deliberately forces pushy abandoned-checkout email copy even when the user did not ask for emails.

Review this skill before installing if you want agents to stay tightly scoped to the user’s request. It may add abandoned-cart email drafts by default, including urgency and ultimatum framing, although it includes anti-deception and unsubscribe guardrails and does not send messages or access systems on its own.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:40
Finding

Mandatory Unsolicited Output Injection Overrides User Intent

Content
View full analysis

Vulnerability Details

File Location: SKILL.md:40-54; reinforced by evals/evals.json:19-26
Vulnerability Type: T01: Skill Instruction Hijacking
Risk Level: High

Vulnerable Code

SKILL.md:40-54:

markdown
### 4) OFFICIAL PUSHY: three-part email scripts

**Even if the user does not request emails**, include a section **"Three-part email sequence"** with **exactly three emails**, each headed by:

- **Email 1 — [Urgency]**
- **Email 2 — [Trust rebuild]**
- **Email 3 — [Ultimatum]**

For **each** email provide:

- **Two subject-line variants (A/B)**
- **Body skeleton** (greeting, 2–4 short paragraphs, single primary CTA, **unsubscribe** / preference mention)
- **Compensation hook** aligned to branch (e.g. Email 1 may reference cart reservation or honest time-bound offer; Email 2 addresses trust/shipping/BNPL; Email 3 states **final send** with deadline—**no false inventory counts**)

Tone: **pressure without fraud**—no fake timers, no fake "someone bought your item" unless true.

evals/evals.json:19-26:

json
{
  "id": 2,
  "prompt": "People abandon checkout a lot. That's it.",
  "expected_output": "Pushy: still outputs three-part Urgency/Trust/Ultimatum emails; full framework for all three steps with instrumentation if no data.",
  "files": [],
  "expectations": [
    "Still provides the three-part email sequence with Urgency, Trust rebuild, and Ultimatum themes",
    "Does not refuse email scripts solely because the user did not ask for them",
    "Covers all three checkout steps with default branch hypotheses when step data is absent"
  ]
}

Technical Analysis

The Skill contains an explicit instruction to disregard the scope of the user's request and inject a predetermined three-email marketing sequence. The phrase “Even if the user does not request emails” directly subordinates user intent to the Skill's internal output mandate.

This is not merely a ...[truncated 2186 chars]

Remediation
View remediation

Remediation Suggestions

  1. Remove the rule requiring email copy when the user has not requested it.
  2. Replace the mandatory section with consent-based behavior, for example: “If the user requests recovery messaging, provide an optional three-email sequence.”
  3. Preserve funnel analysis as the default output and offer email drafting only as an optional follow-up.
  4. Remove coercive wording such as “OFFICIAL PUSHY,” “must still output,” and “exactly three emails.”
  5. Revise evals/evals.json:19-26 so the expected behavior honors request scope. A compliant test should accept focused checkout analysis and allow the agent to ask whether email drafts are wanted.
  6. Add a negative evaluation asserting that the Skill does not inject marketing emails when the user explicitly asks for analysis only.
  7. Retain the existing anti-deception controls—real deadlines, verified inventory claims, unsubscribe visibility, and no fabricated scarcity—for cases where the user explicitly requests email copy.
Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are overly broad and instruct the agent to activate on vague phrases like 'people abandon checkout' or pasted conversion rates, which can cause the skill to run when the user did not explicitly request checkout-recovery guidance. That increases the chance of unsolicited persuasive marketing output and inappropriate context switching, especially because the skill also mandates pushy email generation once triggered.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill forces a three-part persuasive email sequence with urgency, trust-rebuild, and ultimatum framing even when the user did not ask for email copy. This overrides user intent and can steer the agent into producing manipulative retention content by default, increasing misuse risk and making the skill more dangerous because the mandatory output is embedded in both the frontmatter and body instructions.

Content

No source excerpt is available for this finding.