Skills/ClawHub/search-harvester

search-harvester@1.0.2

VERIFIED· install only

Publisher claims: "Candidate discovery for link building and outreach. Harvests candidate URLs from DuckDuckGo HTML and Marginalia through a local privacy-preserving Tor circuit (server IP never contacts the engine), then dedupes, triages liveness/anti-bot barriers, and exports a scored candidate list. DISCOVERY ONLY — this skill never submits forms, posts listings, or performs any state-changing action on third-party sites. Use ONLY when the user explicitly asks to find directories, submission platforms, blogs, or link-building candidates (e.g. "find more places to submit", "find directories", "get candidate websites like scrapebox", "search for link building opportunities"). Requires explicit user confirmation before routing any query through Tor; never for generic web search, never for sensitive/personal queries." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher toniilic · publishing for 99 daysInstalls 544Last detonated 5d ago
$clawhub install search-harvester
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 82/100 (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 · 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

HIGH
Privileged sudo commandSKILL.md:78 · Privileged sudo command — agent may execute with elevated privileges# Verify listening (no sudo needed to list ports):Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandSKILL.md:208 · File permission modification command — agent changes file ownership/permissions- **Use a private output directory.** Default examples use `/tmp`; for real runs prefer `~/harvest/` (chmod 700) — reports contain your queries + candidate URLs.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedscripts/search-harvester.py:56 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/search-harvester.py:65 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Pipe to network utilitySKILL.md:93 · Pipe to network utility — potential reverse shell(echo -e "AUTHENTICATE\r\nSIGNAL NEWNYM\r\nQUIT\r\n"; sleep 2) | nc 127.0.0.1 19051Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈5,204 tok
1 file · 3 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.

search-harvester@1.0.2 safety verdict: Verified (install only) — KillerSkills