Fact Checker
PassAudited by ClawScan on May 1, 2026.
Overview
This skill appears to be a local fact-checking helper, but users should notice that it runs Python commands and reads local project and memory files.
Before installing, make sure you are comfortable with the skill running a local Python script and reading the draft, the hybrid-control-plane project files, git history, localhost status data, and memory/*.md. Treat its suggested corrections as review assistance rather than automatic truth.
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.
When invoked, the agent may run a local Python script and related local commands to produce the fact-check report.
The skill expects the agent to use local command execution to run its bundled checker. This is disclosed and purpose-aligned, but users should know it grants the skill local execution capability.
allowed-tools:\n - Read\n - exec\n...\n1. Run the script with the path to the draft file.
Use it only for drafts and workspaces where local script execution is acceptable, and review generated corrections before applying them.
Setup may depend on local Python/package availability, and the package provenance is not strongly documented in the provided metadata.
The registry metadata provides limited provenance and no install/requirement declaration, while the skill content declares python3 and the script imports requests. This is a review note about packaging clarity, not evidence of hidden behavior.
Source: unknown; Homepage: none; Required binaries (all must exist): none; Install specifications: No install spec
Review the included script before use and install any missing Python dependencies from trusted package sources.
Private or stale memory notes could influence the report, and sensitive details in memory files may be surfaced in fact-check evidence.
The script reads all markdown files in the workspace memory directory and can use that persistent context as evidence during fact-checking.
MEMORY_DIR = WORKSPACE_ROOT / "memory" ... for f in sorted(MEMORY_DIR.glob("*.md")) ... f.read_text()Use this skill only if reading workspace memory logs is acceptable, and independently verify important corrections against primary sources.