Skillv1.0.0

ClawScan security

Reference Maintainer · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 16, 2026, 8:47 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill's files and runtime instructions align with its stated purpose (generating living reference docs); it doesn't request credentials or install external code, but it will read repository/source files and write generated docs and logs to disk, which can capture sensitive data if present.
Guidance: This skill appears to be what it says: a documentation generator that parses source files and writes docs. Before installing or running it, review the included scripts (noted issues: reference_updater.py has a hard-coded default target 'sentiment_decay_model.py' and an indentation bug that may break execution). Important cautions: 1) Run it only on copies or non-sensitive repositories — the tool will read source files and persist extracted configuration (which can include secrets) into references/ and a log file. 2) Limit the paths you pass to the tool and inspect generated output before sharing. 3) If you plan to let an agent invoke this skill autonomously, restrict its file-system access to safe directories. If you want, I can point out the exact lines to change to avoid the hard-coded default and to inspect/escape potential secret-like values before writing them.

Review Dimensions

Purpose & Capability: okName/description match the included Python scripts and templates. The code implements AST/JSON/YAML extraction and generates Markdown/YAML/JSON documentation as advertised. There are no extraneous credentials, binaries, or network calls that contradict the stated purpose.
Instruction Scope: noteSKILL.md and the scripts instruct the agent to parse source files and generate documentation. That is in-scope for a documentation generator, but the code will read arbitrary files you point it at (or the default target in reference_updater.py) and persist extracted config data (including anything that looks like credentials) into references/ and doc_generator.log. Review and restrict the files/paths you allow the skill to access to avoid accidental collection/persistence of secrets.
Install Mechanism: okNo install spec — instruction-only plus included scripts. No packages are downloaded or executed from remote URLs. This minimizes install-time risk.
Credentials: okThe skill declares no required environment variables, credentials, or config paths. The code also does not read environment variables or request external credentials. However, it can extract and persist data from any file it is pointed at, so secrets in source files could be collected as part of normal operation.
Persistence & Privilege: noteThe skill writes output files under references/ and creates a local log file (doc_generator.log) in the working directory. It does not request persistent agent-level privileges or modify other skills. Consider filesystem write implications before running in sensitive directories.