Clear Writing
ReviewAudited by ClawScan on May 10, 2026.
Overview
Prompt-injection indicators were detected in the submitted artifacts (unicode-control-chars); human review is required before treating this skill as clean.
This skill appears safe for normal writing and documentation help. Before installing, verify the source if using the GitHub/npx command, and avoid sending secrets or confidential drafts through the optional subagent copyediting workflow. ClawScan detected prompt-injection indicators (unicode-control-chars), so this skill requires review even though the model response was benign.
Findings (2)
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.
Sensitive draft content could be processed by an internal subagent/model during the suggested copyediting workflow.
The skill may route a user's draft to another agent for copyediting. This is aligned with the writing purpose and no external destination is shown, but drafts can contain private or confidential text.
Dispatch a subagent with your draft and the relevant reference file
Use the subagent workflow only for text you are comfortable having another agent process; remove secrets or confidential details first.
If you install from a moving remote branch, the installed content could differ from the reviewed registry artifact.
The README documents a user-run install command from a GitHub branch/path rather than a pinned immutable version. This is normal installation documentation and not automatic execution by the skill, but users should verify the source.
npx add https://github.com/wpank/ai/tree/main/skills/writing/clear-writing
Prefer the registry install or verify the repository and version before running remote install commands.