Skills/ClawHub/sber-gigachat

sber-gigachat@1.1.2

VERIFIED· install only

Publisher claims: "Integrate GigaChat (Sber AI) with OpenClaw via gpt2giga proxy" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher smvlx · publishing for 259 daysInstalls 1,267Last detonated 54 min ago
$clawhub install sber-gigachat
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 5 of 5 bundled scripts run with no arguments, with decoy credentials in the environment · 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 (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 88/100 (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 · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.0sprocessexited 127: ./scripts/setup.sh: line 3: pip3: command not found
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexited 1:
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1:
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1:
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocess5 of 5 bundled scripts run with no arguments
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocesssecond launch, clock +45 days, CI unset
0.2sprocessexited 127: ./scripts/setup.sh: line 3: pip3: command not found

Static findings

MEDIUM
Process kill commandscripts/start.sh:8 · Process kill command — agent can terminate processesif [ -f "$PID_FILE" ] && kill -0 "$(cat "$PID_FILE")" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/status.sh:3 · Process kill command — agent can terminate processesif [ -f "$PID_FILE" ] && kill -0 "$(cat "$PID_FILE")" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/start-proxy.sh:36 · Process kill command — agent can terminate processes[ -n "$pid" ] && kill -9 $pid 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandSKILL.md:241 · File permission modification command — agent changes file ownership/permissions- **Credentials:** Passed via environment variables only (never on the command line); protect `~/.openclaw/gigachat-new.env` with `chmod 600`Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandscripts/start-proxy.sh:27 · Process kill command — agent can terminate processeskill "$OLD_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/start-proxy.sh:73 · Process kill command — agent can terminate processesif ! kill -0 $NEW_PID 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/stop.sh:4 · Process kill command — agent can terminate processeskill "$(cat "$PID_FILE")" 2>/dev/null && echo "Stopped" || echo "Not running"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈1,525 tok
1 file · 8 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.