Versioned security assessment

Report ID: SA-CA54DA1D

6/30/2026, 2:40:05 AM

gws-docs-write security assessment v2

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
gws-docs-write
Version
v2
Maintainer
googleworkspace
Source
github.com/googleworkspace/cli/tree/main/skills/gws-docs-write/
Coverage
1 Files scanned · 51 Lines analyzed
Policy version
Unavailable

Confirmed finding summary

No confirmed security findings

The completed audit recorded no confirmed security findings. This is not proof that the Skill has no side effects.

Installation context

Historical evidence

This report may not describe the currently installable artifact. Open the current Skill page for install guidance.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

Static analysis flagged Markdown backticks, relative links, and the word Description as dangerous patterns. Review found no malicious code, no prompt injection, and no real cryptographic use. The skill still carries medium risk because it instructs the assistant to run an external Google Workspace CLI command that writes to a Google Docs document.

Report position

Historical report

Open audit history before using this report to install.

Audit attestation

Not attestable

The required immutable binding is incomplete.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

1 Files scanned · 51 Lines analyzed

2 items shown for review

Limitations

This report does not claim runtime or sandbox execution and does not prove the absence of side effects.

Evidence chain

Follow the evidence from source binding to the install contract. Available evidence supports verification; it is not a safety guarantee.

  1. Source

    Binding unavailable

  2. Artifact

    Identity incomplete

  3. Audit

    Complete

  4. Install contract

    Open manifest to verify

    Open manifest

Capabilities observed

Observed means this report recorded supporting evidence. Not recorded does not prove that a capability is absent.

Contains scripts

May execute code included with the Skill.

Not recorded by this audit

Network access

May connect to external services.

Not recorded by this audit

Filesystem access

May read or write local files.

Observed in 3 evidence locations

Env variables

May read values from the process environment.

Not recorded by this audit

External commands

May invoke commands or programs outside the Skill.

Observed in 4 evidence locations

Capability review items (2)
Medium
SKILL.md:22-24SKILL.md:35-37SKILL.md:44-45
External Google Docs Write Command
The skill instructs the assistant to run gws docs +write with a document ID and text. This is legitimate for the skill purpose, but it can modify user documents and should require user confirmation.
The documented command directly performs a Google Docs write action. The file also warns that confirmation is required, which reduces malicious intent concerns.
Low
SKILL.md:16SKILL.md:49-50
Relative Skill References Are Not Path Traversal
The ../ paths point to sibling skill documentation files for shared Google Workspace guidance. They are documentation references, not file reads controlled by user input.
The paths are static Markdown references to nearby skill files. No runtime filesystem API or user-controlled path construction is present.

Risk findings

Confirmed security concerns are separated from items that still need review.

No confirmed security findings were recorded for this completed audit.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit
Unavailable
Content hash
Unavailable
Tree hash
Unavailable
Skill path
Unavailable
Audit payload hash
Unavailable

Analysis metadata

Audit model: codex

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Static false positives ignored (2)
Low
SKILL.md:16SKILL.md:22-24SKILL.md:30-31SKILL.md:35-37
Markdown Backticks Misidentified as Ruby Execution
The static analyzer flagged Markdown inline code and fenced command examples as Ruby or shell backtick execution. No executable Ruby code or command substitution appears in the skill file.
All flagged backticks are Markdown formatting around text or examples. There is no source file that executes Ruby backticks.
Low
SKILL.md:3SKILL.md:28
Weak Cryptography Alerts Are False Positives
The flagged lines contain the word Description in metadata and a Markdown table header. No cryptographic algorithm or crypto operation is present.
The only relevant text is ordinary documentation wording. There is no evidence of DES, MD5, SHA-1, or any other weak cryptographic use.

Verify and export

JSON report CITATION.cff SARIF 2.1.0 Signed installation manifest

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: not_attestable