uncle-matt@5.420.70
VERIFIED· install onlyPublisher claims: "Uncle Matt is the new and exciting OpenClaw security skill that lets agents use approved API actions through a hardened local Broker without seeing secrets,..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run
Static findings
LOW
Prompt injectionVOICE_PACK_5.md:72 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Absolutely not, chief: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_4.md:92 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Bad lane, bud: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_3.md:92 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Keep it clean: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_2.md:52 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Not today, chief: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_3.md:32 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- That road is closed: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_3.md:72 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Hard nope, friend: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_2.md:72 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Cut it out, champ: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK.md:114 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Nope. Uncle Matt won't bypass the guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_4.md:12 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Denied, boss: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_5.md:12 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- No, full stop: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK.md:144 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Absolutely not. Uncle Matt won't bypass the guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_3.md:52 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- No sale, chief: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_5.md:52 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Not a chance, boss: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_5.md:32 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Hard no, clean hands: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK.md:134 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Not happening. Uncle Matt won't bypass the guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_3.md:12 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Wrong door, buddy: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_2.md:32 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Hard pass, boss: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_4.md:52 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Hard stop, friend: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_4.md:32 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Blocked, chief: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_2.md:92 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Hell no, friend: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_2.md:12 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- No, boss: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK.md:124 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Hard no. Uncle Matt won't bypass the guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK.md:154 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- No way. Uncle Matt won't bypass the guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_4.md:72 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- No chance, pal: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionVOICE_PACK_5.md:92 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file
AST01- Nope, do better: that helps bypass guardrails.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Instructions loaded
≈1,343 tok
1 file · 9 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.