Versioned security assessment

Report ID: SA-53704416

7/1/2026, 3:29:29 AM

subagent-driven-development security assessment v2

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
subagent-driven-development
Version
v2
Maintainer
ZhanlinCui
Source
github.com/ZhanlinCui/Ultimate-Agent-Skills-Collection/tree/main/subagent-driven-development
Coverage
4 Files scanned · 403 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 38 potential issues, but review found no malicious code, prompt injection, network calls, or executable scripts. Most findings are false positives from Markdown fences, prompt placeholders, and git SHA labels. The skill remains medium risk because it coordinates subagents that can modify files, run tests, inspect code, and commit changes in a repository.

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

4 Files scanned · 403 Lines analyzed

4 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.

Observed in 3 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 3 evidence locations

Capability review items (4)
Medium
implementer-prompt.md:31-35SKILL.md:49-56SKILL.md:119-120
Agentic Repository Modification Workflow
The skill directs implementer subagents to implement tasks, write tests, verify changes, and commit work. This is expected for a development workflow, but it can change files and invoke project tooling in the active repository.
The cited prompt text clearly asks subagents to perform implementation, testing, and commits. This is legitimate for the skill purpose, but it creates repository modification risk.
Low
code-quality-reviewer-prompt.md:9-18implementer-prompt.md:5-78SKILL.md:14-30SKILL.md:40-83SKILL.md:93-165spec-reviewer-prompt.md:7-61
Markdown Fences Flagged as Backtick Execution
Static external command findings are false positives. The cited sections are Markdown fenced examples and prompt templates, not Ruby or shell backtick execution.
The suspicious characters are Markdown code fences around documentation examples. No executable script, command runner, or interpolation path is present.
Low
implementer-prompt.md:49-65spec-reviewer-prompt.md:28-54
Reconnaissance Findings Are Review Checklist Text
Static reconnaissance findings are false positives. The cited lines ask subagents to compare requirements, inspect code, and validate claims; they do not request system or network enumeration.
The wording is a code review checklist. No commands, endpoints, host discovery, port scanning, or credential discovery instructions were found.
Low
SKILL.md:107
Illustrative Hidden Config Path
Line 107 is an example answer choosing a user-level hook path under ~/.config. It is not a command or automated file access, but it signals possible filesystem interaction when applied to real tasks.
The line is plainly part of a documentation example, not active code. The path is still relevant because the workflow may ask subagents to edit user-level configuration during real tasks.

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 (1)
Low
code-quality-reviewer-prompt.md:15-16implementer-prompt.md:7-25SKILL.md:3SKILL.md:124-131SKILL.md:181spec-reviewer-prompt.md:9
Weak Cryptography Findings Are False Positives
The cited lines contain task labels, headings, ordinary prose, or git SHA placeholders. They do not define cryptographic algorithms or security logic.
Manual review found no MD5, SHA-1, or other weak cryptographic implementation. The only SHA-related text is a git commit reference placeholder.

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