Back to skill

Security audit

Chapter Outliner

Security checks for vulnerabilities and agentic risk

Overview

This skill mostly does what it claims, but it ships an undocumented LLM mode that can send local manuscript/project content to Alibaba DashScope without clear user consent.

Review before installing. Use the documented local generator for confidential manuscripts, and treat generate_outline_llm.py as a remote mode that may send story outlines, style settings, character profiles, and chapter metadata to DashScope if invoked with a DASHSCOPE_API_KEY. Pin dependencies before production use.

Vulnerability Patterns
  • 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
  • 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
Findings (2)

other

Warning
Location
scripts/generate_outline_llm.py:62
Finding

Undisclosed Transmission of Project Content to a Third-Party LLM Service

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
scripts/requirements.txt:1
Finding

Unpinned Third-Party Dependencies Produce Non-Reproducible Installations

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
Findings (12)

Tainted flow: 'headers' from os.environ.get (line 116, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/generate_outline_llm.py (reported line 140)May include surrounding context.

python
transient=True,
    ) as progress:
        progress.add_task("generating", total=None)
        response = requests.post(url, headers=headers, json=payload, timeout=120)

    response.raise_for_status()
    data = response.json()

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description and overview instruct users in Chinese, effectively imposing a specific language on users without any opt-in or alternative language path. The policy allows locale constraints only when they are explicitly offered as a choice or clearly justified as region-specific, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code file contains natural-language descriptions and console output entirely in Chinese, beginning with the module docstring. The file does not offer a language/locale option or explain that it is intentionally limited to a Chinese-language audience, which can violate a policy requiring user language choice or opt-in.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This script reads a credential from the environment and sends outline, style, character, and chapter content to a third-party LLM service. In the skill context, that is a meaningful data-exposure behavior because the manifest describes an outline generator without clearly warning that local project content will be transmitted off-host to an external provider.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The code performs a remote LLM call using project content but does not present a clear user-facing warning or consent prompt before transferring that content externally. Users may reasonably assume a local content-processing tool unless told otherwise, making this a privacy and transparency issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The system prompt is written to require output in Chinese-context instructions and does not offer any language or locale choice to the user. This is a natural-language policy concern because the skill hardcodes a specific language behavior rather than allowing user selection or documenting a justified locale restriction.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This is a direct external transmission of locally loaded project content to a remote service. In this skill context, the transmission is intentional for functionality, but it is still security-relevant because it moves potentially sensitive user content outside the local environment.

Content

Scanner excerpt · scripts/generate_outline_llm.py (reported line 140)May include surrounding context.

python
transient=True,
    ) as progress:
        progress.add_task("generating", total=None)
        response = requests.post(url, headers=headers, json=payload, timeout=120)

    response.raise_for_status()
    data = response.json()

Ssd 3

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The prompt is built by embedding project text and character data directly into the message sent to the external LLM. That can disclose private manuscript content, notes, and character details to the provider, and because the input is untrusted text, it also increases prompt-injection exposure that may alter model behavior or cause over-sharing of included context.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
95% confidence
Finding

The dependency 'rich' is unpinned, which makes builds non-reproducible and allows future installs to pull in unexpected or vulnerable releases. While this is not an immediate exploit by itself, it increases supply-chain risk and can introduce breaking or insecure behavior over time.

Content

Scanner excerpt · scripts/requirements.txt (reported line 1)May include surrounding context.

text
rich
PyYAML

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
99% confidence
Finding

The dependency 'PyYAML' is unpinned, and this is more concerning because PyYAML has a history of security issues in some versions, including unsafe deserialization-related flaws. Without pinning, installations may resolve to affected or unreviewed versions, creating avoidable supply-chain and runtime risk.

Content

Scanner excerpt · scripts/requirements.txt (reported line 2)May include surrounding context.

text
rich
PyYAML

Unverifiable Dependency: PyYAML has 8 known advisory(ies) (CVE-2019-20477 (Deserialization of Untrusted Data in PyYAML); CVE-2020-1747 (Improper Input Validation in PyYAML); CVE-2020-14343 (Improper Input Validation in PyYAML) +5 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
98% confidence
Finding

PyYAML has multiple known advisories, and because the manifest does not specify a version, there is no way to verify whether the installed package is vulnerable. In a content-generation skill, YAML may plausibly be used for configuration or prompt data, so unresolved PyYAML version risk is relevant even though exploitability depends on how the library is used.

Content

No source excerpt is available for this finding.