Real Skill packageSource verifiedClawHub registry

Sentinel Modality-Router Redaction Check

Confirms Sentinel's PII redaction guardrail survives routing through a modality-aware LiteLLM router to two different self-hosted model types -- a text model (Ollama) and a vision model (SmolVLM-Instruct) -- picked automatically by whether the request contains an image. Checks both redaction and rou

Identity and source

Publisher attributionMark-Stadtmuellerregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 59% rule confidence
Package forminstruction with code5 recorded files
Canonical sourceClawHub registryclawhub:mark-stadtmueller:sentinel-modality-router-check
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/25/2026.claude/skills/sentinel-modality-router-check

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/25/2026.agents/skills/sentinel-modality-router-check

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/25/2026skills/sentinel-modality-router-check

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @mark-stadtmueller/sentinel-modality-router-check
clawhub inspect @mark-stadtmueller/sentinel-modality-router-check --version 1.0.1

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
4 / 5 inspected as text
Checked
8/25/2026, 1:54:37 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highPackage contains a path commonly used for secrets.env.example · confidence 88%.env.example
1 High/Critical review queue entry
STATIC_SENSITIVE_FILE_IN_PACKAGEpending
Open human review queue →
6 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • external write action — automatically inferred
6 dependency and API indicators
  • pypi: requests >=2.31,<3
  • pypi: python-dotenv >=1.0,<2
  • api: api.telegram.org
  • api: clawhub.ai
  • api: docs.superwise.ai
  • api: host.docker.internal
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/24/2026, 8:43:49 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:fa31777c6aef8ed42968a88d5dde76816a750550b0af20d65d6dcc4a1f0b5d08
Show up to 5 recorded paths
  • .env.example
  • requirements.txt
  • skill-card.md
  • SKILL.md
  • skill.py

Source changelog

Version 1.0.1 - Documentation update: clarified behavioral details in SKILL.md, specifically disclosing that the skill stops/restarts the gateway container and may send up to 300 characters of backend response to Telegram. - No code or functional changes; all behavior remains the same.