Skills/ClawHub/fraud-filter

fraud-filter@0.4.0

VERIFIED· install only

Publisher claims: "Community trust scores for AI agent payment endpoints — checks endpoint reputation before payment and queues anonymous failure reports locally (network repor..." Observed in sandbox: calls api.fraud-filter.com only, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher mattpolly · publishing for 214 daysInstalls 883Last detonated 38 min ago
$clawhub install fraud-filter
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 12 bundled scripts run with no arguments (the rest were not run: per-bundle cap), 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 89/100 (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: calls api.fraud-filter.com only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexec /usr/bin/dirname
0.0sprocessexited 1: Usage: check-endpoint.sh <endpoint-url> [--price <amount>]
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexec /usr/bin/mkdir
0.1sprocessexec /usr/bin/rm
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1: Outcomes: success, post_payment_failure, pre_payment_failure
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexec /usr/bin/dirname
0.2sprocessbundled script run in the sandbox with no arguments
0.5snetworkCONNECT tcp://api.fraud-filter.com:443
0.5sprocessexec /usr/bin/dirname
0.5sprocessexec /usr/bin/mkdir
0.5sprocessexec /usr/bin/mv
0.5sprocessexec /usr/bin/chmod
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocessexec /usr/bin/dirname
0.6sprocessexec /usr/bin/cat
0.6sprocessbundled script run in the sandbox with no arguments
0.7sprocessexec /usr/bin/dirname
0.7sprocessexec /usr/bin/cat
0.7sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.8sprocess8 of 12 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.8sprocessscript backend runs setup only
0.8sprocessscript backend runs setup only
0.8sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionhooks/after-payment.sh:54 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('fraud-filter: auto-reported post_payment_failure for ' + hostname + ' (empty/error response).');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandscripts/dashboard.sh:47 · Process kill command — agent can terminate processesif [ -f "$PID_FILE" ] && kill -0 "$(cat "$PID_FILE")" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/dashboard.sh:36 · Process kill command — agent can terminate processeskill "$PID"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/dashboard.sh:22 · Process kill command — agent can terminate processesif [ -f "$PID_FILE" ] && kill -0 "$(cat "$PID_FILE")" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/sync-trust-db.sh:75 · File permission modification command — agent changes file ownership/permissionschmod 600 "$DB_PATH"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandscripts/dashboard.sh:35 · Process kill command — agent can terminate processesif kill -0 "$PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈1,941 tok
1 file · 21 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.

fraud-filter@0.4.0 safety verdict: Verified (install only) — KillerSkills