Skills/ClawHub/rss-personalized-digest

rss-personalized-digest@1.0.0

VERIFIED· install only

Publisher claims: "每天自动抓取多源RSS,根据关键词权重筛选并生成带点击追踪跳转的个性化摘要,用户点击自动加权优化推送。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher pasaidon · publishing for 216 daysInstalls 750Last detonated 11 h ago
$clawhub install rss-personalized-digest
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
2 of 2 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 90/100 (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 · 2 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /app/apps/web/node_modules/.bin/ssh
0.1sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/ssh
0.1sprocessexec /app/node_modules/.bin/ssh
0.1sprocessexec /pnpm/ssh
0.1sprocessexec /usr/local/sbin/ssh
0.1sprocessexec /usr/local/bin/ssh
0.1sprocessexec /usr/sbin/ssh
0.1sprocessexec /usr/bin/ssh
0.1sprocessexec /sbin/ssh
0.1sprocessexec /bin/ssh
0.1sprocessexited 1: Node.js v22.23.5
0.1sprocessbundled script run in the sandbox with no arguments
2.1sprocessexec /usr/bin/grep
2.1sprocessexited 1: ./start.sh: line 23: ss: command not found
2.1sprocess2 of 2 bundled scripts run with no arguments
2.1sprocessscript backend runs setup only
2.1sprocessscript backend runs setup only
2.1sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandSKILL.md:312 · Process kill command — agent can terminate processeskill $(ps aux | grep "rss-redirect" | grep -v grep | awk '{print $2}') 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:221 · Process kill command — agent can terminate processeskill $(ps aux | grep "rss-redirect-server" | grep -v grep | awk '{print $2}') 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:230 · Process kill command — agent can terminate processeskill $(ps aux | grep "serveo.net" | grep -v grep | awk '{print $2}') 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈2,096 tok
1 file · 5 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.

rss-personalized-digest@1.0.0 safety verdict: Verified (install only) — KillerSkills