Versioned security assessment

Report ID: SA-C014D1B6

7/4/2026, 3:57:03 PM

content-quality-auditor security assessment v1

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
content-quality-auditor
Version
v1
Maintainer
aaron-he-zhu
Source
github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/seo-geo/optimize/content-quality-auditor
Coverage
3 Files scanned · 661 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

2 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.

Most static filesystem and command findings are false positives caused by Markdown links, code fences, inline field names, and templates. Confirmed risks are limited to a connector command that fetches user-controlled URLs and a mutable raw GitHub fallback; semantic review also found automatic memory persistence that needs safeguards.

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

3 Files scanned · 661 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 5 evidence locations

Filesystem access

May read or write local files.

Observed in 21 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 48 evidence locations

Capability review items (3)
Medium
SKILL.md:98-131
Ruby/shell backtick execution
**Zero-dependency rendered fetch (keyless)**: with no crawler connected, `python3 "${CLAUDE_PLUGIN_R
Line 98 contains a concrete python3 connector command with a user-provided <url> placeholder. The intended connector is legitimate, but an unquoted user URL in a shell example leaves command-execution risk if followed literally.
Medium
SKILL.md:199
Hardcoded URL
*Standalone install fallback*: if that relative path does not exist, this skill was installed standa
Line 199 tells standalone installs to fetch runbook instructions from raw.githubusercontent.com on the mutable main branch. This creates a remote instruction dependency, even though it does not send user data.
Low
SKILL.md:98
Fetch API call
**Zero-dependency rendered fetch (keyless)**: with no crawler connected, `python3 "${CLAUDE_PLUGIN_R
Line 98 directs the agent to fetch user-provided or authorized URLs through a local connector. It states robots.txt limits, but outbound requests based on user input still need network-boundary controls.

Risk findings

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

Confirmed security concerns (2)

RISK-001 Medium
SKILL.md:199
Mutable Remote Instruction Fallback
The standalone fallback tells agents to fetch runbook and reference instructions from raw.githubusercontent.com on the main branch. Mutable remote Markdown can change skill behavior after marketplace review.
The file explicitly names a raw GitHub main-branch fallback for instruction files. The risk is contextual supply-chain drift rather than direct exfiltration, so confidence is high but not absolute.
RISK-002 Medium
SKILL.md:87SKILL.md:98SKILL.md:437
Automatic Persistent Memory Writes From Audit Results
The skill tells agents to promote audit blockers into persistent memory without user confirmation. Because audited content can be untrusted, this can preserve hostile or misleading content-derived text for later agent runs.
Lines 87 and 437 require persistent memory writes, and line 98 identifies fetched content as untrusted. The exact payload stored depends on runtime audit output, so the finding is medium confidence.

Remediation

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

  1. FIX-001
    Medium
    Connector command accepts a user-provided URL in a shell example.
    Quote the URL argument in the command example and require the connector to reject localhost, private IP ranges, and non-HTTP schemes before fetching.
  2. FIX-002
    Medium
    Standalone fallback loads instruction files from a mutable GitHub main branch.
    Bundle the runbook with the skill, or pin remote fallback URLs to a release tag and verify a documented content hash before use.
  3. FIX-003
    Medium
    Audit results are promoted to persistent memory without user confirmation.
    Ask before writing hot-cache or open-loop memory, and strip raw untrusted page text from saved summaries.

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