Nlp
PassAudited by ClawScan on May 1, 2026.
Overview
This appears to be a local NLP helper that processes user-provided text or files, with minor packaging notes but no artifact-backed malicious behavior.
This skill looks appropriate for local text analysis. Before installing, note that it runs a bundled bash script and can read any file path you provide, so only point it at documents you are comfortable having analyzed and shown in output.
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.
If used on sensitive documents, their contents or derived excerpts may appear in terminal output, logs, or downstream agent context.
The skill can process local files or piped content through a shell command. This is expected for NLP document processing, but users should be aware that selected file contents are read and output locally.
All commands accept input via three methods: ... `--file path.txt` — read from a file ... Pipe via stdin
Use it only on files you intend to analyze, and avoid sending highly sensitive documents through agent workflows unless that is acceptable.
The skill may fail or behave differently on systems lacking the expected shell utilities, even though the registry metadata says there are no required binaries.
The metadata does not declare runtime tools, while SKILL.md documents Bash 4+, grep -P, and awk requirements and the manifest includes scripts/script.sh. This is an under-declared runtime/dependency detail, not evidence of malicious behavior.
Required binaries (all must exist): none ... Install specifications: No install spec — this is an instruction-only skill.
Verify the bundled script and local shell utilities before use; maintainers should align metadata, SKILL.md requirements, and script versioning.