Audit History

The review confirmed four unsafe ZIP extraction calls that can permit Zip Slip when processing a crafted Office archive. The remaining static matches are false positives from OOXML namespaces, templates, documentation, or local document-processing operations; no prompt injection, credential theft, or network exfiltration was found. Static review was capped at 400/460 representative findings; omitted static matches are unconfirmed, so automatic publishing stays disabled until manual review.

The skill is a legitimate DOCX and OOXML toolkit, but it contains real operational risks. I confirmed unguarded archive extraction and privileged dependency install instructions. Most other static alerts are false positives from XML namespaces, schema imports, Markdown backticks, or OOXML identifiers. Static review was capped at 400/460 representative findings; omitted static matches are unconfirmed, so automatic publishing stays disabled until manual review.

The skill is primarily a legitimate DOCX and OOXML document-processing toolkit, and many static alerts are false positives from Markdown examples, XML namespaces, and schema files. Real risk remains in unsafe ZIP extraction of user-supplied Office archives and incomplete path normalization in relationship handling. The instructions also include non-core promotional and cross-skill AI generation guidance that should be removed or gated by explicit user consent. Static review was capped at 400/460 representative findings; omitted static matches are unconfirmed, so automatic publishing stays disabled until manual review.

Most static alerts are OOXML namespace, schema, XML ID, or documentation false positives. I confirmed unsafe archive extraction of user-supplied Office files, active sudo and global install instructions, and a low-severity environment search command. The bundled evaluation.json also contains audit-style safe-publish claims that should be removed from marketplace content.

The skill has legitimate DOCX and OOXML document-processing intent, and many static alerts are false positives from markdown code blocks, XML namespaces, and OOXML vocabulary. However, several bundled scripts extract user-supplied Office archives with extractall() and no member path validation, which is a confirmed Zip Slip risk. Publication should wait until archive extraction is hardened and privileged install guidance is removed or clearly isolated.

This is a legitimate document processing skill with no security concerns. All 1146 static findings are false positives: documentation code blocks (pandoc, soffice commands), OOXML schema namespace URLs, and XML attribute names misidentified as crypto/C2 patterns. The code uses safe XML parsing (defusedxml) to prevent XXE attacks.

This is a legitimate document processing skill with no security concerns. All 1146 static findings are false positives: documentation code blocks (pandoc, soffice commands), OOXML schema namespace URLs, and XML attribute names misidentified as crypto/C2 patterns. The code uses safe XML parsing (defusedxml) to prevent XXE attacks.

This is a legitimate document processing skill with no security concerns. All static findings are false positives: documentation code blocks (pandoc, soffice commands), OOXML schema namespace URLs, and XML attribute names misidentified as crypto/C2 patterns. The code uses safe XML parsing (defusedxml) to prevent XXE attacks.

This is a legitimate document processing skill with controlled filesystem access and secure XML parsing. Uses defusedxml library to prevent XXE attacks. External commands (soffice, git) are called with hardcoded paths and controlled arguments. Operations are confined to user-specified files within designated workspaces.