Skills/ClawHub/prompt-injection-defense

prompt-injection-defense@1.0.0

CAUTION

Publisher claims: "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)." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher deyogaid · joined 0 days agoInstalls 0Last detonated 3 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-05 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Instructs the agent to modify its persistent memory or instruction files; Prompt injection attempt; Leet speak prompt injection. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:58 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injection attemptSKILL.md:33 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptreferences/canary-patterns.md:11 · Prompt injection attempt — model control tokens · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptreferences/canary-patterns.md:9 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Leet speak prompt injectionreferences/canary-patterns.md:9 · Leet speak prompt injection — obfuscated 'override instructions'Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01

Cost to the agent

Instructions loaded
≈819 tok
1 file · 6 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim deyogaid: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim deyogaidPropose a patch to the maintainer