Versioned security assessment

Report ID: SA-02F077C1

7/5/2026, 7:15:43 AM

agent-generation security assessment v7

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
agent-generation
Version
v7
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

1 confirmed security finding requires 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.

The static backtick, reconnaissance, and device-file alerts are false positives from Markdown documentation and read-only analysis examples. No prompt injection or malicious exfiltration intent was found. The remaining concern is that generated agent templates grant broad write, shell, and network tools by default.

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

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

    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 8 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 115 evidence locations

Risk findings

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

Confirmed security concerns (1)

RISK-001 Medium
SKILL.md:56examples/tech-stack-expert.md:101examples/architecture-expert.md:137examples/domain-expert.md:129
Overbroad Generated Agent Tool Permissions
The skill template and examples assign generated agents broad tools including Edit, Write, Bash, WebFetch, and WebSearch. This can enable unnecessary file modification, shell execution, or network access if copied into agents without review.
The same broad tool list appears in the core template and all three example agents. The risk depends on downstream publication, but the evidence is direct.

Remediation

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

  1. FIX-001
    Medium
    Generated agents receive broad tool permissions by default.
    Use the minimum tool set for each role and remove Bash, Write, Edit, WebFetch, or WebSearch unless that role clearly needs them.
  2. FIX-002
    Low
    Documented shell snippets may be copied into sensitive repositories.
    Label shell examples as optional read-only inspection steps and advise users to review commands before execution.

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