Versioned security assessment

Report ID: SA-02BE9409

8/9/2026, 9:23:16 AM

advanced-evaluation security assessment v8

Skill Security Certification Report

Audit History
Scanner version 3.0.0 Audit model: codex Latest published report
Skill name
advanced-evaluation
Version
v8
Maintainer
muratcankoylan
Source
github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/skills/advanced-evaluation
Coverage
6 Files scanned · 1,784 Lines analyzed
Policy version
skillstore-security-audit-policy-v1

Highest confirmed finding severity

Medium

1 confirmed security finding requires attention.

Installation context

Check the current Skill page

This page summarizes report evidence only. The Skill page provides the canonical install advisory.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

All 44 static alerts are false positives caused by Markdown formatting, ordinary collection methods, evaluation terminology, and research links. The local example script only calculates and prints demonstration results. However, evaluator prompts interpolate untrusted candidate responses without explicit prompt-injection isolation, which could permit scoring manipulation.

Report position

Latest published report

Latest refers to the report sequence, not to artifact currentness.

Audit attestation

Active attestation

A public attestation is available for this exact report.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

6 Files scanned · 1,784 Lines analyzed

1 item 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

    Commit and path bound

  2. Artifact

    Content and tree hashes bound

  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 4 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.

Observed in 33 evidence locations

Risk findings

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

Confirmed security concerns (1)

RISK-001 Medium
SKILL.md:84-109scripts/evaluation_example.py:64-93scripts/evaluation_example.py:195-217
Evaluator Prompt Injection Exposure
The examples interpolate candidate responses directly into judge prompts without telling the judge to treat embedded directives as untrusted data. A crafted response could manipulate scores or bypass rubric instructions.
The prompt templates visibly place candidate-controlled text in evaluator context without instruction-isolation guidance. This is a recognized scoring-integrity weakness, although exploitation depends on the judge model.

Remediation

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

  1. FIX-001
    Medium
    Candidate responses are inserted directly into evaluator prompts without explicit instruction isolation.
    Delimit candidate content, label it as untrusted data, forbid following embedded instructions, and test judges with adversarial response fixtures.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit
02be9409c79ca1183f7844009c14d9df684d0cf9
Content hash
8b9e3d9de07a0505ae2b42df2e15dd75bab5f2486e336194481c558e0648ded0
Tree hash
91c7180c92732df01e16fca1d52c15842d9bf8bd8323517b4e4a5789cc554839
Skill path
skills/muratcankoylan/advanced-evaluation
Audit payload hash
abed176587115b8d885cff5218fb6853

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 Signed attestation CITATION.cff SARIF 2.1.0 Signed installation manifest Source

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: active