Skills/ClawHub/agent-skill-evolution

agent-skill-evolution@1.0.1

VERIFIED· install only

Publisher claims: "Gunakan saat user secara eksplisit meminta evolusi skill lewat benchmark, red-teaming, dan regresi pada task tertentu." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher pmuhammadagus-byte · publishing for 83 daysInstalls 510Last detonated 6d ago
$clawhub install agent-skill-evolution
WatchReport an issue

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 2026-11-08 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 deviations
t+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

CRITICAL
Prompt injectionSKILL.md:96 · Prompt injection — known jailbreak technique reference- [ ] ACTION selesai DAN GOAL tercapai (bedakan "command sukses" ≠ "goal tercapai").Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:152 · Prompt injection — known jailbreak technique reference… → AGENTIC → FUTURE-READY** melalui benchmark, red-teaming, regression testing, dan iterative refinement — dengan **rollback safety** sebagai jaminan stabilitas. …Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:36 · Prompt injection — known jailbreak technique reference4. "Skill `openclaw-backup` usang, evaluasi dan buat candidate replacement."Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:34 · Prompt injection — known jailbreak technique reference2. "Skill `trading-analyst` sering gagal di edge case, lakukan red-team dan perbaiki."Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:4 · Prompt injection — known jailbreak technique referencedescription: "Gunakan saat user secara eksplisit meminta evolusi skill lewat benchmark, red-teaming, dan regresi pada task tertentu."Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈5,847 tok
1 file · 4 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.