skill-creator@r1

CAUTION

Publisher claims: "Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry skills.shPublisher anthropics · joined 2 days agoInstalls 414KLast detonated 41 h ago

Dispute verdict

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

Static findings

MEDIUM

File type combined with upload actionagents/grader.md:103 · File type combined with upload action — agent may exfiltrate local data files

AST07

MEDIUM

File type combined with upload actionSKILL.md:205 · File type combined with upload action — agent may exfiltrate local data files

AST07

MEDIUM

File type combined with upload actionscripts/run_loop.py:313 · File type combined with upload action — agent may exfiltrate local data files

AST07

HIGH

URL with embedded credentialseval-viewer/viewer.html:9 · URL with embedded credentials — may be phishing or credential leaking

AST07

HIGH

URL with embedded credentialsassets/eval_review.html:9 · URL with embedded credentials — may be phishing or credential leaking

AST07

HIGH

Process kill commandSKILL.md:287 · Process kill command — agent can terminate processes

AST05

HIGH

Python subprocess execution detectedeval-viewer/generate_review.py:291 · Python subprocess execution detected

AST05

CRITICAL

HTML comment carrying imperative instructions to the agenteval-viewer/viewer.html:623 · HTML comment carrying imperative instructions to the agent

AST01

HIGH

Python subprocess execution detectedscripts/run_eval.py:85 · Python subprocess execution detected

AST05

HIGH

Python subprocess execution detectedscripts/improve_description.py:35 · Python subprocess execution detected

AST05

HIGH

URL with embedded credentialsscripts/generate_report.py:41 · URL with embedded credentials — may be phishing or credential leaking

AST07

MEDIUM

File type combined with upload actionagents/grader.md:83 · File type combined with upload action — agent may exfiltrate local data files

AST07

HIGH

Process kill commandeval-viewer/generate_review.py:445 · Process kill command — agent can terminate processes

AST05