Versioned security assessment

Report ID: SA-762E87DE

6/30/2026, 10:44:45 AM

ai-engineer security assessment v2

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
ai-engineer
Version
v2
Maintainer
sickn33
Source
github.com/sickn33/antigravity-awesome-skills/tree/main/skills/ai-engineer
Coverage
1 Files scanned · 172 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 reported weak cryptography, reconnaissance, and jailbreak-keyword patterns in SKILL.md. Manual review found these are defensive or descriptive Markdown references, not executable code, command usage, network access, or prompt injection. No confirmed malicious behavior or hidden semantic risk 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 · 172 Lines analyzed

0 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.

Not recorded by this audit

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.

Not recorded by this audit

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 (3)
Low
SKILL.md:3SKILL.md:15SKILL.md:28SKILL.md:122SKILL.md:144SKILL.md:155SKILL.md:166SKILL.md:170
False Positive: Weak Cryptographic Algorithm
Verdict: FALSE_POSITIVE. The flagged lines are natural-language references to AI architecture, system design, and production practices. They do not mention or implement weak cryptographic algorithms and contain no executable code.
The file is a Markdown instruction document with no crypto implementation or configuration. The flagged terms appear in benign phrases such as architecture and design guidance.
Low
SKILL.md:34SKILL.md:56SKILL.md:164
False Positive: System Reconnaissance
Verdict: FALSE_POSITIVE. The flagged lines discuss protecting sensitive data, BM25 hybrid search, and an example RAG request. They do not instruct collection of host details, credentials, network inventory, or environment data.
The surrounding context is AI safety and retrieval-system design. I found no commands, scripts, or data exfiltration paths connected to reconnaissance behavior.
Low
SKILL.md:86
False Positive: Known Jailbreak Keyword
Verdict: FALSE_POSITIVE. The flagged term appears in a defensive safety capability for jailbreak detection, content filtering, and bias mitigation. It does not ask the model to bypass instructions or skip security review.
The exact context is defensive prompt safety guidance. No override language, fake system message, or instruction to ignore prior instructions was found.

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