Versioned security assessment

Report ID: SA-75E202BC

6/29/2026, 3:12:41 AM

agent-generation security assessment v6

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
agent-generation
Version
v6
Maintainer
Cpicon
Source
github.com/Cpicon/claude-code-plugins/tree/main/agent-team-creator/skills/agent-generation
Coverage
6 Files scanned · 1,160 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.

Static analysis reported many command, filesystem, and weak-crypto patterns, but the weak-crypto findings are false positives from markdown words such as description and Design. The remaining risk is medium because the templates grant generated agents Bash, file editing, and web tools, and the analysis guide includes local enumeration commands for codebase inspection.

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 · 1,160 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 6 evidence locations

Filesystem access

May read or write local files.

Observed in 6 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 10 evidence locations

Risk findings

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

Confirmed security concerns (2)

RISK-001 Medium
SKILL.md:43-49references/agent-templates.md:37references/agent-templates.md:87references/agent-templates.md:136references/agent-templates.md:181references/agent-templates.md:225
Generated Agents Receive Broad Tool Permissions
The core template and reference templates include Bash, Edit, Write, WebFetch, and WebSearch in generated agent tool lists. This is useful for coding agents, but it enables command execution, file modification, and network access when a generated agent is installed.
The cited lines explicitly grant broad tools to generated agents. The context is legitimate developer assistance, so the risk is capability exposure rather than confirmed malicious intent.
RISK-002 Medium
references/analysis-patterns.md:9-12references/analysis-patterns.md:113-125references/analysis-patterns.md:163-173references/analysis-patterns.md:179-187
Codebase Enumeration Commands In Analysis Guidance
The analysis guide includes shell commands that list directories, search source files, and read schema files. These commands support the skill purpose, but they can expose project structure and sensitive model details if used without consent.
The shell commands are visible and perform local codebase discovery. They are ordinary analysis commands, so the security concern depends on the workspace sensitivity.

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 (2)
Low
SKILL.md:3SKILL.md:81references/agent-templates.md:68-71references/analysis-patterns.md:28-33examples/tech-stack-expert.md:25
Static Weak-Crypto Findings Are False Positives
The high-severity weak-crypto alerts match ordinary markdown words such as description, Design, and domain-description. No evidence found of cryptographic implementation, weak hashing, encryption, or password handling logic in the cited files.
Targeted review found only descriptive markdown text at the flagged locations. There is no executable crypto code or algorithm selection.
Low
examples/tech-stack-expert.md:5-105examples/architecture-expert.md:5-140examples/domain-expert.md:5-133references/agent-templates.md:7-41references/analysis-patterns.md:9-12
Markdown Code Fences Trigger External Command Alerts
Most external command alerts come from markdown fences, inline paths, and documentation examples. The skill does not include scripts or executable source files, but users should still review generated agents before enabling broad tools.
The reviewed files are markdown documentation and templates. Some fenced bash examples exist, but there is no packaged script that executes them automatically.

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