Real Skill packageSource verifiedClawHub registry

prompt-injection-defense

Harden agent sessions against prompt injection from untrusted content. Use when the agent reads web search results, emails, downloaded files, PDFs, or any external text that could contain adversarial instructions. Provides content scanning, memory write guardrails (scan → lint → accept or quarantine), untrusted content tagging, and canary detection. Also use when setting up new tools that ingest external content (email checkers, RSS readers, web scrapers).

Identity and source

Publisher attributionDeyogaidregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 70% rule confidence
Package forminstruction with code7 recorded files
Canonical sourceClawHub registryclawhub:deyogaid:prompt-injection-defense
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 · 11/6/2026.claude/skills/prompt-injection-defense

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 · 11/6/2026.agents/skills/prompt-injection-defense

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 · 11/6/2026skills/prompt-injection-defense

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 @deyogaid/prompt-injection-defense
clawhub inspect @deyogaid/prompt-injection-defense --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
7 / 7 inspected as text
Checked
11/6/2026, 6:36:35 AM
Scanner
0.1.3
Policy
1.0.3
2 automated findings
mediumPrompt-override language requires reviewSKILL.md:33 · confidence 62%Ignore previous instructions
mediumPrompt-override language requires reviewreferences/canary-patterns.md:9 · confidence 62%ignore previous instructions
3 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
1 dependency and API indicators
  • api: clawhub.ai
External clawhub result: suspicious

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
11/5/2026, 8:43:54 PM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

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

Package content hashsha256:c3e3e01c8591c7b32465918eaa9c48abcfaf1b61e84f2bcc01dd477c6b2db4ab
Show up to 7 recorded paths
  • _meta.json
  • references/canary-patterns.md
  • scripts/safe-memory-write.sh
  • scripts/scan-content.py
  • scripts/tag-untrusted.sh
  • skill-card.md
  • SKILL.md

Source changelog

- Added `_meta.json`. - Removed `skill-card.md`. - `SKILL.md` is unchanged.