Security audit
Security checks for vulnerabilities and agentic risk
This skill is a local Word document reader with optional user-directed text export and no evidence of hidden network, persistence, credential access, or destructive behavior.
Reasonable to install if you need local Word document text extraction. Treat Word files from untrusted sources carefully because document parsers can have vulnerabilities, and consider pinning dependency versions before production use. Use --output only with paths you intend to create or overwrite.
The README is written entirely in Chinese and explicitly emphasizes Chinese support, but does not offer any language choice or explain a region-specific requirement. This can violate a language/locale policy when users are not given an opt-in or alternative language option.
The skill advertises optional write behavior via --output, but the manifest does not declare a corresponding tool scope such as explicit write permissions or allowed-tools. This creates a trust and policy gap: users or orchestrators may assume the skill is read-only while it can write files, increasing the risk of unintended file creation or overwriting in local workflows.
The description emphasizes Chinese support in a way that could be read as privileging a specific language/locale. Because the file does not explicitly state that other languages are also supported or that Chinese handling is optional, this can create a mild language-policy concern in natural-language documentation.
This file's natural-language documentation and usage examples are entirely in Chinese, with no indication that language choice is optional or that the skill is region-specific. That can violate a language/locale policy requiring user choice or documented justification for a forced locale.
This manifest describes what the skill can do, but it does not provide any activation conditions, scope limits, or exclusion examples. In a manifest file, the absence of specific trigger phrasing or contextual constraints can make invocation behavior ambiguous for systems that rely on description text for routing.
The description explicitly highlights Chinese support, which may imply a locale-specific behavior preference without stating that language handling is optional or user-selected. While not severe, this can conflict with language/locale policy expectations when no opt-in or broader language choice is described.
The dependency is specified with a lower bound only, which allows future installs to resolve to different versions over time and makes builds non-reproducible. In a document-parsing skill, this increases supply-chain and maintenance risk because a later vulnerable or incompatible release could be installed without review.
python-docx>=0.8.11
olefile>=0.46
python-docx has known historical advisories related to XML external entity handling, and because the manifest does not pin a version, it is impossible to verify from this file alone whether a safe release will be installed. This skill's purpose is to read untrusted Word documents, which makes parser/library vulnerabilities more relevant because attacker-supplied files are the direct input surface.
This dependency is also unpinned, so installations are not reproducible and may pull in unexpected future releases. While not an immediate exploit by itself, it weakens supply-chain control and can expose the skill to newly introduced vulnerabilities or breakage.
python-docx>=0.8.11
olefile>=0.46
No suspicious patterns detected.