Versioned security assessment

Report ID: SA-0C1FF8FE

7/5/2026, 2:58:04 PM

gws-docs security assessment v4

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
gws-docs
Version
v4
Maintainer
googleworkspace
Source
github.com/googleworkspace/cli/tree/main/skills/gws-docs/
Coverage
1 Files scanned · 50 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.

The skill intentionally uses the external gws CLI to inspect and operate on Google Docs, including commands that can read or write documents with user credentials. Most static hits are Markdown backtick false positives, but the relative references to sibling skill files create an audit-boundary risk because behavior depends on content outside this package.

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 · 50 Lines analyzed

5 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.

Observed in 1 evidence location

Filesystem access

May read or write local files.

Observed in 2 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 10 evidence locations

Capability review items (5)
High
SKILL.md:16
Path traversal sequence
> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If mis
Line 16 directs the agent to read ../gws-shared/SKILL.md outside this skill directory. That is not arbitrary user path traversal, but it makes behavior depend on unaudited adjacent content.
High
SKILL.md:26
Path traversal sequence
| [`+write`](../gws-docs-write/SKILL.md) | Append text to a document |
Line 26 links to ../gws-docs-write/SKILL.md as a helper for append operations. The relative parent path crosses the audited package boundary and may pull in unreviewed instructions.
Medium
SKILL.md:16
Ruby/shell backtick execution
> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If mis
Line 16 instructs running the external gws generate-skills command if shared instructions are missing. This is intended setup behavior, but it can modify local skill files through an installed CLI.
Medium
SKILL.md:18-20
Ruby/shell backtick execution
```bash
The bash block describes running gws docs with resource, method, and flags. That command can access Google Docs with the user's credentials, including write-capable methods.
Medium
SKILL.md:40-46
Ruby/shell backtick execution
```bash
The bash block contains gws docs --help and gws schema commands. The arguments are constrained and mostly introspective, but this is still external CLI execution.

Risk findings

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

No confirmed security findings were recorded for this completed audit.

Remediation

Suggested fixes recorded by this audit. Applying them is the maintainer’s responsibility.

  1. FIX-001
    High
    The skill references sibling skill files outside this audited package.
    Package the shared and helper instructions with this skill or declare them as audited dependencies without relative parent paths.
  2. FIX-002
    Medium
    External gws commands can read or modify Google Docs.
    Require explicit user confirmation before write operations and document the Google Workspace scopes needed for each workflow.
  3. FIX-003
    Medium
    The setup note tells agents to run gws generate-skills if shared instructions are missing.
    Ask users to run setup manually and review generated files before the agent loads or follows them.

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.

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