Skills/ClawHub/no-barnacles

no-barnacles@0.2.2

CAUTION

Publisher claims: "Memory and safety discipline for long-running agents: hot/cold memory index, STATE.md working memory, incident ledger, injection contract. Setup or repair." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher cnayotte · joined 0 days agoInstalls 156Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-10-27 and scored it 55/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection attempt; Prompt injection attempt; Prompt injection attempt. 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

CRITICAL
Prompt injection attemptdocs/safety-layers.md:89 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attempttemplates/AGENTS.skeleton.md:12 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptdocs/safety-layers.md:7 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectiontemplates/AGENTS.skeleton.md:17 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agenttemplates/STATE.template.md:3 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Fake instruction boundary tagtemplates/AGENTS.skeleton.md:15 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injection attemptdocs/safety-layers.md:13 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filestemplates/AGENTS.skeleton.md:130 · 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 attempttemplates/AGENTS.skeleton.md:15 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filestemplates/AGENTS.skeleton.md:141 · 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
HIGH
Authorization escalation languagetemplates/AGENTS.skeleton.md:17 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

What would make this Verified

25 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 cnayotte: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cnayotte