Versioned security assessment

Report ID: SA-4CC56079

7/5/2026, 1:27:52 AM

writing-bots security assessment v7

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
writing-bots
Version
v7
Maintainer
ApeWorX
Source
github.com/ApeWorX/skills/tree/main/silverback/writing-bots
Coverage
1 Files scanned · 94 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

High

1 confirmed security finding requires 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.

Most Markdown backtick detections are false positives from inline documentation terms and code fences. The confirmed concerns are Silverback installation and run commands, environment-variable configuration, and autonomous blockchain transaction capability. No prompt injection or data exfiltration intent was found.

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

6 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 3 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 11 evidence locations

Capability review items (5)
Medium
SKILL.md:74
Ruby/shell backtick execution
To install silverback, run the following command with `uv` installed:
This line introduces installation of Silverback with an external command. Installing a CLI changes the user environment and may fetch executable code from a package source.
Medium
SKILL.md:76-78
Ruby/shell backtick execution
```bash
The fenced command block contains uv tool install silverback. That is real command execution that installs executable tooling, even though it is a legitimate setup step.
Medium
SKILL.md:81
Ruby/shell backtick execution
You can then run the bot on the `ecosystem` and `network` they want (such as "ethereum:mainnet") usi
This line instructs running the bot on a selected blockchain network using the Silverback CLI. Running a bot can connect to live networks and trigger automated actions.
Medium
SKILL.md:83-85
Ruby/shell backtick execution
```bash
The fenced command block contains silverback run with a target network argument. That executes a bot against a blockchain network and may perform configured actions.
Low
SKILL.md:67
Python environment access
Also, you should suggest things like adding configurable limits (using environment variables via `os
The skill recommends using os.environ to read environment-variable configuration for limits. This is legitimate but security-sensitive because generated bots must avoid reading or logging secrets accidentally.

Risk findings

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

Confirmed security concerns (1)

RISK-001 High
SKILL.md:34-38SKILL.md:60-68
Autonomous Blockchain Transaction Risk
The skill guides bots that may sign and broadcast transactions on public blockchains. Faulty logic or weak safeguards could trigger irreversible on-chain actions.
Lines 34-38 explicitly include signing and broadcasting transactions, and lines 60-68 discuss signer access and risk controls. This is an intended capability, so confidence is high even though it is not malicious by itself.

Remediation

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

  1. FIX-001
    High
    Generated bots may sign and broadcast blockchain transactions.
    Default generated examples to read-only or dry-run behavior. Add spending limits, signer checks, staged testing, and circuit breakers before enabling transaction submission.
  2. FIX-002
    Medium
    The skill includes commands to install and run Silverback tooling.
    Require explicit user confirmation before running uv tool install or silverback run. Pin or verify Silverback versions when possible.
  3. FIX-003
    Low
    Environment variables may contain sensitive configuration.
    Read only named variables, document required values, and avoid printing or sending environment values to logs or external services.

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