Skills/Glama/anabolic

anabolic@r1

CAUTION

Publisher claims: "A task manager's view of a Windows or Linux PC for AI assistants: processes, per-core CPU and who ran on it, disks and the files they serve, network connections and DNS lookups, GPUs, sensors, services, stutters and a 7-day history. Actions (ending or suspending processes, controlling services, memory dumps) are allowed kind by kind, and it runs locally over stdio or on 127.0.0.1 only." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher raptortwentyone · joined 0 days agoInstalls 0Last detonated 1 h ago
What would fix thisWatchDispute verdict

Is anabolic@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Outbound HTTP to raw IP address; Outbound HTTP to raw IP address; README tells the reader to click past SmartScreen. 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

MEDIUM
URL using raw IP addresscrates/anabolic/src/mcp/mod.rs:183 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addresscrates/anabolic/src/mcp/mod.rs:221 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Outbound HTTP to raw IP addresscrates/anabolic/src/mcp/server.rs:53 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandcrates/anabolic/src/cli.rs:6 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Outbound HTTP to raw IP addresscrates/anabolic/src/mcp/mod.rs:221 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)crates/anabolic/src/mcp/mod.rs:220 · MCP server using network transport (SSE/HTTP) — data sent over networkFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill commandcrates/anabolic/src/dialogs.rs:75 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
README tells the reader to click past SmartScreenREADME.md:171Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Outbound HTTP to raw IP addresscrates/anabolic/src/mcp/mod.rs:183 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addresscrates/anabolic/src/mcp/server.rs:53 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈36 tok
1 file · 81 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

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. README tells the reader to click past SmartScreen≈ +9 on the totalPin versions and sources; vendor anything fetched at install time.
  2. Unclaimed publisher≈ +8 on the totalClaim raptortwentyone: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  4. URL using raw IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim raptortwentyonePropose a patch to the maintainer