Skills/ClawHub/pageskim

pageskim@1.0.0

VERIFIED· install only

Publisher claims: "Make a website readable by LLMs and agents at 10-50x fewer tokens by generating PageSkim .llm.md sibling files for its pages. Use when the user asks to "make my site agent-readable", "add llm.md / llms.txt-style files / PageSkim to my site", "reduce token costs for agents or AI crawlers reading my s" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher venki0552 · publishing for 131 daysInstalls 502Last detonated 3d ago
$clawhub install pageskim
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 2026-11-12 and scored it 88/100 (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

MEDIUM
npx invocation of non-well-known packagescripts/generate-and-validate.sh:14 · npx invocation of non-well-known package — may execute untrusted codenpx --yes pageskim "${ARGS[@]}"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionSKILL.md:3 · File type combined with upload action — agent may exfiltrate local data files…ges. Use when the user asks to "make my site agent-readable", "add llm.md / llms.txt-style files / PageSkim to my site", "reduce token costs for agents or AI crawlers reading my site", or "optimize my site for AI agents". Detects the site …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:40 · npx invocation of non-well-known package — may execute untrusted codenpx pageskim generate <output-dir> --json --split --site-index --base-url <site-url>Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:17 · npx invocation of non-well-known package — may execute untrusted codeEverything runs through `npx pageskim` (published on npm) — no permanentFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:27 · npx invocation of non-well-known package — may execute untrusted code| `next.config.*` | Next.js | `out/` (needs `output: "export"`) — see note | `npx next build` |Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:26 · npx invocation of non-well-known package — may execute untrusted code| `astro.config.*` | Astro | `dist/` | `npx astro build` |Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/generate-and-validate.sh:20 · npx invocation of non-well-known package — may execute untrusted codeif ! npx --yes pageskim validate "$page" "$sibling"; thenFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:62 · npx invocation of non-well-known package — may execute untrusted codehugo && npx --yes pageskim generate public --site-index --base-url <site-url>Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈1,107 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.