Versioned security assessment

Report ID: SA-656BE304

8/8/2026, 9:10:43 AM

localhero security assessment v7

Skill Security Certification Report

Audit History
Scanner version 3.0.0 Audit model: codex Latest published report
Skill name
localhero
Version
v7
Maintainer
localheroai
Source
github.com/localheroai/agent-skill/tree/main/
Coverage
5 Files scanned · 340 Lines analyzed
Policy version
skillstore-security-audit-policy-v1

Highest confirmed finding severity

Medium

2 confirmed security findings require 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.

Most static findings are Markdown false positives involving inline code, example identifiers, and legitimate Localhero.ai links. The skill does direct agents to execute an external npm package, upload source strings, and handle an API key, including one unsafe command-line option.

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

5 Files scanned · 340 Lines analyzed

9 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

    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.

Observed in 6 evidence locations

External commands

May invoke commands or programs outside the Skill.

Observed in 24 evidence locations

Capability review items (7)
High
SKILL.md:86
Generic API/secret keys
For non-interactive environments, they can also use `npx @localheroai/cli login --api-key <key>` or
The guidance permits placing a real API key in a command argument, where it may be retained in shell history or exposed to process inspection.
Medium
SKILL.md:30
Ruby/shell backtick execution
- Otherwise, run `npx @localheroai/cli translate --changed-only`. This translates only keys that dif
The skill explicitly directs the agent to run an npx package that contacts a translation service and modifies project translation files.
Medium
SKILL.md:72-76
Ruby/shell backtick execution
Run `npx @localheroai/cli glossary --output json` to get the project glossary. Use these terms consi
The line explicitly tells the agent to execute the Localhero npm CLI to retrieve glossary data from the external project.
Medium
SKILL.md:76-82
Ruby/shell backtick execution
Run `npx @localheroai/cli settings --output json` to get the project's tone, style, and language set
The line explicitly invokes the external Localhero npm CLI to retrieve project settings.
Medium
SKILL.md:82-84
Ruby/shell backtick execution
```bash
The cited block contains an npx login command that launches an external npm package for authentication.
Medium
SKILL.md:86
Ruby/shell backtick execution
For non-interactive environments, they can also use `npx @localheroai/cli login --api-key <key>` or
The line recommends executing an external npm CLI with an API-key argument. Command arguments may be exposed through shell history or process inspection.
Medium
SKILL.md:92-97
Ruby/shell backtick execution
```bash
The cited shell block invokes the Localhero npm CLI in non-interactive mode and can create configuration or import project files.

Risk findings

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

Confirmed security concerns (2)

RISK-001 Medium
SKILL.md:28-30cli-reference.md:16-24
Project Source Strings Sent to External Service
The translation workflow runs a third-party CLI that may send changed source strings to Localhero.ai without an explicit confirmation step.
The workflow explicitly directs translation execution, and the CLI reference states that push sends source files to Localhero.ai.
RISK-002 Medium
cli-reference.md:111
Credential File Deletion Guidance
The CLI reference advises removing .localhero_key to override stale authentication, which could delete a local credential without a recovery step.
The line directly instructs removal of a named credential file, although it does not provide the deletion command.

Remediation

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

  1. FIX-001
    High
    Authentication guidance permits passing an API key as a command argument.
    Remove command-line key guidance and recommend a protected environment variable or secret manager.
  2. FIX-002
    Medium
    The skill executes @localheroai/cli through npx without a pinned version.
    Pin an audited CLI version and require user confirmation before commands that upload or modify files.
  3. FIX-003
    Medium
    Translation commands may upload source strings to Localhero.ai.
    Disclose uploaded data and request confirmation before sending project content to the external service.
  4. FIX-004
    Medium
    The CLI reference advises removing a stale credential file.
    Require explicit user approval before deleting .localhero_key and provide a non-destructive credential selection option.

Expert evidence

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

Artifact subject

Marketplace commit
656be3040aef5c047555a908cd5c695d22a4a548
Content hash
652c74d09d4cbd7c46c70a7167337e62b31c7a81227db78ec215cfd883caf688
Tree hash
78e64c5ddfee8f5398dc8598c5b49570527abf97cff6e5054677fa3b582ddadb
Skill path
skills/localheroai/localhero
Audit payload hash
5ca3a832d16c8db633607622e608348e

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