Versioned security assessment

Report ID: SA-7C753F63

6/30/2026, 6:04:49 PM

slack-automation security assessment v2

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
slack-automation
Version
v2
Maintainer
sickn33
Source
github.com/sickn33/antigravity-awesome-skills/tree/main/skills/slack-automation
Coverage
1 Files scanned · 190 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

3 confirmed security findings require attention.

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 static shell-execution and weak-crypto findings are false positives caused by Markdown code spans, Slack tool names, and words such as desc. The confirmed risk is legitimate but sensitive networked Slack automation through Rube MCP, including message posting, searching, user listing, reactions, and scheduling after OAuth authorization.

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 · 190 Lines analyzed

3 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 2 evidence locations

Filesystem access

May read or write local files.

Not recorded by this audit

Env variables

May read values from the process environment.

Not recorded by this audit

External commands

May invoke commands or programs outside the Skill.

Not recorded by this audit

Risk findings

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

Confirmed security concerns (3)

RISK-001 Medium
SKILL.md:14-25SKILL.md:34-40SKILL.md:106-132
Authorized Slack Workspace Mutations
The skill instructs agents to send, edit, schedule, thread, and react to Slack messages through an authorized Rube MCP Slack connection. This is expected functionality, but misuse or overly broad OAuth scopes could create unwanted workspace changes.
The tool sequences explicitly include Slack send, edit, schedule, and reaction actions. The behavior is legitimate for the skill, but it can modify Slack state when authorized.
RISK-002 Medium
SKILL.md:60-64SKILL.md:83-89SKILL.md:162-170
Authorized Slack Data Retrieval
The skill directs agents to search messages, fetch threads, list users, list channels, and retrieve workspace metadata. These actions can expose sensitive workspace content within the granted Slack scopes.
The cited workflows clearly retrieve messages, threads, users, channels, and team metadata. The risk depends on granted OAuth scopes, but the data access capability is direct and intentional.
RISK-003 Low
SKILL.md:20
Third-Party MCP Endpoint Is Explicit and User Configured
The skill tells users to configure the Rube MCP endpoint. This is a real network dependency, but it is not hidden and there is no evidence of covert exfiltration in the skill text.
The hardcoded URL is visible setup documentation for the required MCP server. Network use is intentional, but no secret harvesting or concealed outbound destination was found.

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:15-16SKILL.md:35-40SKILL.md:176-189
Static Shell Execution Matches Are Markdown False Positives
The repeated Ruby or shell backtick findings are Markdown inline code spans around Slack and Rube tool names, parameters, and response fields. No executable script, shell command, or Ruby code was found in SKILL.md.
The matching characters appear in Markdown prose and table entries, not code blocks or executable files. The skill contains only SKILL.md documentation and no runnable Ruby or shell script.
Low
SKILL.md:3SKILL.md:50-52SKILL.md:70SKILL.md:188
Weak Cryptography and Reconnaissance Matches Are Text False Positives
The high cryptography findings map to ordinary words or Slack parameters, and the reconnaissance findings map to documented Slack response fields and validation text. No cryptographic implementation, system probing, or local host enumeration was found.
The cited lines are natural-language descriptions, Slack API parameters, or quick-reference table rows. I found no hashing, encryption, process discovery, network scanning, or system reconnaissance behavior.

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