web-capture@0.2.0
VERIFIED· install onlyPublisher claims: "Keep your company context current from your website and competitors' pages: each Monday your site, competitors' pages and news about both land in context/ as one pull request; the first run seeds positioning, offerings, an inferred ICP with a disqualifier, competitors, clients and proof, and every later run adds a dated note of what changed, never editing an existing file. Triggers: "keep our context current from our website", "watch competitor pricing pages", "add our company news to the knowledge base", "our context repo is empty, seed it from our website", "set up the workspace context from our domain". Cargo project, harness claudeCode, parallel, GitHub. Skip when: news about target accounts, which is monitor-buying-signals; one company researched before a call, which is research-account; or the ICP verified against won and lost deals, which is win-loss-review." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
What changed since 0.1.2
vet-skills diff web-capture 0.1.2 0.2.0In the sandbox, this version reached for nothing 0.1.2 did not. Compared from the two recorded runs, not from source.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
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 2026-11-16 and scored it 81/100 (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 deviationsStatic findings
…leave `state` unset and deploy binds the project's connected state (`cargo.state.json`): its repository, directory and production branch. `cargo-ai project check` prints the binding; a project whose state is not connected deploys the agent…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.…he shape `cargo-ai project init` scaffolds). Nothing here needs a credential in .env, and nothing here reads a CRM, a call or Slack." homepage: https://github.com/g…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.on PATH, otherwise npx --yes @cargo-ai/cli in its place in every commandFix: Pin versions and sources; vendor anything fetched at install time.nothing to `.env.example`:** nothing here holds a credential.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.| A harness does not bring its own model; this is what the weekly run is billed and metered against |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.| A page not listed is a change never seen |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
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.