discord-soul@1.0.0
CAUTION· static onlyPublisher 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.
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 onlyThis 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
- **Direct injection:** "Ignore previous instructions and..."Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- `<system>`, `[INST]`, `<<SYS>>`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- System prompt injection (`<system>`, `[INST]`, `<<SYS>>`)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.3. 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.- `DAN mode`, `jailbreak`, `bypass`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- System prompt injection (`<system>`, `[INST]`, `<<SYS>>`)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- `ignore previous instructions`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- **Jailbreaks:** "DAN mode", "developer mode"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Direct instructions ("Ignore previous instructions and...")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- `<system>`, `[INST]`, `<<SYS>>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- **Jailbreaks:** "DAN mode", "developer mode"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- Jailbreak attempts ("DAN mode", "developer mode")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- **System injection:** `<system>`, `[INST]`, `<<SYS>>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Jailbreak keywordsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- Jailbreak attempts ("DAN mode", "developer mode")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- **System injection:** `<system>`, `[INST]`, `<<SYS>>`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
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%- 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.
- 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.