Skills/ClawHub/discord-soul

discord-soul@1.0.0

CAUTION· static only

Publisher claims: "Create a living agent from your Discord server. The agent embodies your community's identity, remembers every conversation, and grows as the community evolves. Talk to your Discord as if it were a person." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher kgeesawor · publishing for 283 daysInstalls 1,831Last detonated 5 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-19 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: Prompt injection attempt; Authorization escalation language; 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

CRITICAL
Prompt injection attemptSKILL.md:68 · Prompt injection attempt — 'ignore previous instructions'- **Direct injection:** "Ignore previous instructions and..."Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptreferences/security.md:45 · Prompt injection attempt — model control tokens · informational: not an instruction file- `<system>`, `[INST]`, `<<SYS>>`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Fake instruction boundary tagreferences/security.md:14 · Fake instruction boundary tag · informational: not an instruction file- System prompt injection (`<system>`, `[INST]`, `<<SYS>>`)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesscripts/simulate_growth.py:147 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file3. Update the agent files (SOUL.md, MEMORY.md, etc.) as the prompt instructsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionreferences/security.md:46 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- `DAN mode`, `jailbreak`, `bypass`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptreferences/security.md:14 · Prompt injection attempt — model control tokens · informational: not an instruction file- System prompt injection (`<system>`, `[INST]`, `<<SYS>>`)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptreferences/security.md:42 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file- `ignore previous instructions`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Authorization escalation languageSKILL.md:71 · Authorization escalation language- **Jailbreaks:** "DAN mode", "developer mode"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injection attemptreferences/security.md:11 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file- Direct instructions ("Ignore previous instructions and...")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Fake instruction boundary tagreferences/security.md:45 · Fake instruction boundary tag · informational: not an instruction file- `<system>`, `[INST]`, `<<SYS>>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injectionSKILL.md:71 · Prompt injection — known jailbreak technique reference- **Jailbreaks:** "DAN mode", "developer mode"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/security.md:15 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- Jailbreak attempts ("DAN mode", "developer mode")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:70 · Fake instruction boundary tag- **System injection:** `<system>`, `[INST]`, `<<SYS>>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injectionSKILL.md:84 · Prompt injection — known jailbreak technique reference- Jailbreak keywordsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languagereferences/security.md:15 · Authorization escalation language · informational: not an instruction file- Jailbreak attempts ("DAN mode", "developer mode")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injection attemptSKILL.md:70 · Prompt injection attempt — model control tokens- **System injection:** `<system>`, `[INST]`, `<<SYS>>`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈2,175 tok
2 files · 20 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 kgeesawor: 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 kgeesaworPropose a patch to the maintainer