Truthcheck
PassAudited by ClawScan on May 1, 2026.
Overview
Truthcheck is a coherent fact-checking CLI skill, but users should verify the external CLI package and understand optional provider API/key use before installing.
This skill appears purpose-aligned and not malicious from the provided artifacts. Before installing, verify the external `truthcheck` package, only configure API keys you actually need, and avoid checking sensitive claims or private URLs through external providers unless that data sharing is acceptable.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Installing or using the skill may require trusting a separate package whose contents are not shown in these artifacts.
The skill relies on an external `truthcheck` CLI/package, but the reviewed artifacts do not include the package code, an install spec, or a homepage/source reference. This is a provenance check for the user, though using a CLI is central to the skill's purpose.
Source: unknown; Homepage: none ... No install spec — this is an instruction-only skill ... Required binaries (all must exist): truthcheck
Verify the `truthcheck` package source and maintainer before installing, and prefer a pinned or known-good version from a trusted package index.
If configured, the CLI may use your provider accounts, quotas, or billing for fact-checking and search features.
The skill documents optional API keys for LLM and search integrations. These credentials are expected for the stated functionality, but they still represent delegated access to third-party services.
`GEMINI_API_KEY` ... `OPENAI_API_KEY` ... `ANTHROPIC_API_KEY` ... `BRAVE_API_KEY`
Use least-privileged keys where possible, monitor usage, and only set the provider keys needed for the features you intend to use.
Private or sensitive claims and URLs could leave the local environment when using external LLM or search-backed checks.
The skill supports external LLM and search providers for analysis and search results. This is purpose-aligned, but claim text, URLs, or related queries may be processed by those services.
truthcheck verify "some claim" --llm openai ... `--search brave` gives better search results than default DuckDuckGo
Avoid submitting confidential material unless you are comfortable with the relevant provider's data handling; consider local/offline options such as Ollama when suitable.