Skills/Glama/kato

kato@r1

VERIFIED

Publisher claims: "Lets an agent working in a client's folder query transcripts, notes, commitments, briefs and search results from that client's recorded calls, so it can ask what was said, shown and promised without pasting anything. Folder bindings restrict every tool to the bound client, and answers are redacted by default." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher manduks · joined 0 days agoInstalls 0Last detonated 2 h ago
$npx skills add kato
WatchReport an issue

Is kato@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 90/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. 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
Process kill commandhooks/session-start.sh:30 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandhooks/session-start.sh:34 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandhooks/session-start.sh:36 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈655 tok
1 file · 11 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.