other
- 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
Security audit
Security checks for vulnerabilities and agentic risk
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.
scripts/generate_outline_llm.py:62Undisclosed Transmission of Project Content to a Third-Party LLM Service
scripts/requirements.txt:1Unpinned Third-Party Dependencies Produce Non-Reproducible Installations
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.
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()
Without declared permissions the skill's intent is opaque and cannot be validated.
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.
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.
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.
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.
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.
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.
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()
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.
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.
rich
PyYAML
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.
rich
PyYAML
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.