Real Skill packageSource verifiedClawHub registry

Prompt Injection Containment

Contain prompt injection by removing capabilities, not by detection — tool-less LLM subprocess, fenced data, code-checked output, HMAC approvals. For agents reading untrusted text.

Identity and source

Publisher attributionAlexandre Blochregistry owner unverified by skillvetai
Functional categoryWriting, Content & Translationautomatically inferred · 56% rule confidence
Package forminstruction with code3 recorded files
Canonical sourceClawHub registryclawhub:alexbloch-ia:prompt-injection
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 · 10/1/2026.claude/skills/prompt-injection

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 · 10/1/2026.agents/skills/prompt-injection

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 · 10/1/2026skills/prompt-injection

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 @alexbloch-ia/prompt-injection
clawhub inspect @alexbloch-ia/prompt-injection --version 1.0.0

Security evidence

SkillVetAI static result: medium 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
3 / 3 inspected as text
Checked
10/1/2026, 5:50:22 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
mediumPrompt-override language requires reviewSKILL.md:128 · confidence 62%IGNORE PREVIOUS INSTRUCTIONS
4 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
1 dependency and API indicators
  • api: clawhub.ai
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
9/30/2026, 9:42:38 AM
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:d9a7bcea43f026c66b5f01c439abcdbacffd5da355241ae90842e32f9abceb7a
Show up to 3 recorded paths
  • scripts/contain.py
  • skill-card.md
  • SKILL.md

Source changelog

Initial release: capability-removal containment for LLM steps reading untrusted text (observed claude -p flag matrix on 2.1.285, sandbox cwd, fenced payload, code-validated output, HMAC single-use approvals, argv discipline, read-only inputs) + stdlib reference module with 65-fixture selftest.