Back to skill

Security audit

Daily English Card

Security checks for vulnerabilities and agentic risk

Overview

This skill openly performs the stated daily card workflow, but it depends on unaudited local scripts and sends/uploads content automatically to fixed external services.

Review before installing. Configure your own WeChat recipient, bot account, cron job, and IMA knowledge base; verify or package the referenced scripts and credential helpers; pin dependencies; and enable automatic sending/uploading only if you are comfortable with daily external transmission and retention of generated cards.

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 (4)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:20
Finding

Unpinned Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
`. - Maintain a lockfile containing all transitive dependencies. - Require cryptographic hashes through pip's `--require-hashes` option. - Use an explicitly configured and trusted package index. - Install dependencies in an isolated virtual environment rather than the global interpreter environment. - Add a documented update and security-review process before changing dependency versions. ]]>

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:30
Finding

Execution of Mutable Scripts Outside the Audited Skill Package

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:55
Finding

Hard-Coded External WeChat Recipient and Bot Account

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
README.md:241
Finding

Unaudited Credential and External Upload Helper Chain

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README specifies Chinese titles, Chinese translations, Chinese prompt text, and a fixed Asia/Shanghai schedule for the skill, but does not indicate that users can choose another language or locale. Under the policy, forcing a specific language or locale without opt-in is a natural-language policy concern unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README explicitly describes automatic upload of generated cards to Tencent IMA and automatic delivery to WeChat, but it does not mention consent, disclosure, opt-out behavior, or data handling boundaries. Even if the card content seems low sensitivity, automatic external transmission and archival create privacy and compliance risk because user-generated or personalized study content may be sent to third-party services without clear notice.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The documented curl command sends media to a WeChat target through a local gateway using a bearer token, which is a real example of external data transmission. In this skill's context, that transmission is expected functionality, but it is still security-relevant because it enables outbound delivery of generated content and could be misused if tokens, targets, or media paths are altered or if users are not aware of the transmission.

Content

Scanner excerpt · README.md (reported line 312)May include surrounding context.

md
# 2. 发送到微信
TOKEN=$(bash ~/.qclaw/scripts/get-token.sh)
curl -X POST "http://localhost:{GATEWAY_PORT}/api/v1/messages/send" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The public description says the skill pushes cards to WeChat every morning, but it does not clearly warn that generated content is sent automatically to a fixed recipient/account without per-use confirmation. This creates a consent and data-disclosure risk, since users may invoke or install the skill without realizing it performs scheduled outbound delivery to a specific external channel.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description defines the skill as generating and pushing English learning cards, which imposes a fixed language mode without indicating user choice or opt-in. Under the stated policy, forcing a specific language can be a locale/language policy issue unless the constraint is explicitly justified or optional.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description mentions automatic upload to IMA for archival, but it does not present this as a clear privacy/security warning or explain the external retention implications. Automatic archival to a knowledge base increases data exposure and persistence, and the skill context makes this more sensitive because uploads happen by default and are treated as non-blocking rather than consent-gated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes very broad phrases such as “口语”, “学英语”, and “背单词”, which are common in normal conversation and can cause accidental activation. In this skill, unintended activation is more dangerous because the workflow performs automatic external actions, including generating content and pushing it to a fixed WeChat recipient.

Content

No source excerpt is available for this finding.