Versioned security assessment

Report ID: SA-07121211

6/28/2026, 9:51:44 AM

writing-bots security assessment v6

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
writing-bots
Version
v6
Maintainer
ApeWorX
Source
github.com/ApeWorX/skills/tree/main/silverback/writing-bots
Coverage
1 Files scanned · 94 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 correctly identified network access, environment-variable guidance, and external command examples, but the weak cryptography and Ruby backtick alerts are false positives from Markdown prose. The skill has legitimate blockchain automation intent, but it can lead users to install a CLI, run bots, use API keys, and broadcast transactions, so publication should include a clear operational risk warning.

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 · 94 Lines analyzed

4 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.

Observed in 1 evidence location

External commands

May invoke commands or programs outside the Skill.

Observed in 3 evidence locations

Capability review items (4)
Medium
SKILL.md:74-85
External CLI Installation and Bot Execution
TRUE_POSITIVE: The skill instructs assistants to install Silverback with uv and run a bot using the Silverback CLI. This is legitimate for the skill purpose, but it can execute local project code and connect to blockchain networks.
The command guidance is explicit and directly tied to bot execution. The surrounding text frames it as normal Silverback usage, not hidden execution.
Medium
SKILL.md:34-40SKILL.md:60-68
Blockchain Transaction and External Service Automation
TRUE_POSITIVE: The skill describes bots that may send POST requests, use communication services, and sign or broadcast blockchain transactions. These actions are domain-appropriate but high-impact if generated code is not reviewed and tested.
The text clearly names external service calls and transaction broadcasting. It also includes risk controls, which supports legitimate intent but does not remove operational risk.
Low
SKILL.md:16-19
Documentation Network Fetch Is Legitimate
TRUE_POSITIVE: The skill tells assistants to fetch current Silverback documentation from ApeWorX URLs. This is a network dependency, but it targets public vendor documentation and supports accurate code generation.
The URLs are visible, public documentation links. I found no evidence that the network request transmits secrets or user data.
Low
SKILL.md:64-68
Environment Variable Access for Runtime Configuration
TRUE_POSITIVE: The skill suggests operational modes and limits based on environment variables such as API keys. This is common configuration practice, but generated bots must avoid logging or transmitting secret values.
The environment-variable reference is explicit, but it is framed as configuration and risk management. No evidence shows secret exfiltration.

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:3SKILL.md:7-9SKILL.md:18SKILL.md:23SKILL.md:64
False Positive: Weak Cryptography Alerts
FALSE_POSITIVE: The static weak-cryptography findings point to prose, URLs, and metadata, not cryptographic algorithms or insecure crypto APIs. No evidence found of MD5, SHA-1, DES, RC4, or related weak cryptographic use.
The cited lines contain natural-language descriptions and documentation references. There is no cryptographic code on those lines.
Low
SKILL.md:16SKILL.md:63-68SKILL.md:76-83
False Positive: Markdown Backtick Execution Matches
FALSE_POSITIVE: Most Ruby backtick execution alerts are Markdown inline code or fenced code formatting, not Ruby code. The actual shell commands are documented separately as an operational medium-risk finding.
The file is Markdown and the backticks delimit tool names, Python identifiers, and command examples. There is no Ruby execution context in the skill file.

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