Skills/ClawHub/agentic-browser

agentic-browser@0.1.5

VERIFIED· install only

Publisher claims: "Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: we..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher okaris · publishing for 274 daysInstalls 2,870Last detonated 3 h ago
$clawhub install agentic-browser
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
3 of 3 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 84/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexited 1: ./templates/authenticated-session.sh: line 22: 1: Usage: ./templates/authenticated-session.sh <login-url>
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexited 1: ./templates/capture-workflow.sh: line 16: 1: Usage: ./templates/capture-workflow.sh <url> [output-dir]
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: ./templates/form-automation.sh: line 16: 1: Usage: ./templates/form-automation.sh <form-url>
0.1sprocess3 of 3 bundled scripts run with no arguments
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiontemplates/capture-workflow.sh:149 · File type combined with upload action — agent may exfiltrate local data filesls -la "$OUTPUT_DIR"/*.txt "$OUTPUT_DIR"/*.json 2>/dev/null || trueFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Remote installer piped to shellSKILL.md:17 · Remote installer piped to shellcurl -fsSL https://cli.inference.sh | sh && infsh loginFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:275 · npx invocation of non-well-known package — may execute untrusted codenpx skills add inference-sh/skills@web-searchFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:278 · npx invocation of non-well-known package — may execute untrusted codenpx skills add inference-sh/skills@llm-modelsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Pipe-to-shell patternSKILL.md:17 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -fsSL https://cli.inference.sh | sh && infsh loginFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06

Cost to the agent

Instructions loaded
≈2,489 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.