Versioned security assessment

Report ID: SA-016C708D

7/6/2026, 5:09:05 PM

entity-optimizer security assessment v2

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
entity-optimizer
Version
v2
Maintainer
aaron-he-zhu
Source
github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/protocol/entity-optimizer
Coverage
6 Files scanned · 545 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.

Most static findings are false positives caused by markdown code fences, inline code, relative documentation links, and schema terminology. Two findings are confirmed because the skill recommends local Python connector helpers that run with user-derived values. No prompt injection, credential access, or data exfiltration intent was found in the reviewed files.

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

6 Files scanned · 545 Lines analyzed

2 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.

Observed in 11 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 26 evidence locations

Capability review items (2)
Medium
SKILL.md:88
Ruby/shell backtick execution
**Zero-dependency local helper** (keyless): `python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/kg.py
The skill directs the agent to run python3 with a local Knowledge Graph connector and an entity argument. This is intended helper use, but it is real external command execution from user-provided input.
Medium
SKILL.md:90
Ruby/shell backtick execution
**Keyless attention + mention series**: once `kg.py reconcile` names the exact Wikipedia article, `p
The skill directs the agent to run pageviews.py and gdelt.py helper scripts using an article title or entity name. The commands are quoted, but they execute local scripts and perform public lookups from user-derived values.

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
    Medium
    Optional Python connector helpers execute local commands.
    Require explicit user confirmation before running helpers, avoid shell interpolation, and pass entity values as argv.
  2. FIX-002
    Low
    Connector helpers may perform live public lookups.
    Document network access for Wikidata, pageviews, and GDELT helpers, and keep an offline user-to-run path.
  3. FIX-003
    Low
    Saved entity profile paths are derived from entity names.
    Normalize slugs and reject path separators before writing any profile under memory/entities.

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