Back to skill
Skillv2.1.1
ClawScan security
Chro Advisor · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 10, 2026, 8:47 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's files, instructions, and requirements are consistent with an HR/CHRO advisory toolkit that runs local Python modeling scripts and reference docs; nothing in the package requests unrelated credentials, installs, or external downloads.
- Guidance
- This package appears to be a legitimate CHRO advisory tool that runs local Python models and ships useful reference material. Before installing or running it: (1) inspect the two Python scripts locally (they expect JSON input) and run them on sample/test data first; (2) do not feed real employee PII/compensation data to an untrusted agent or remote service—run in an isolated/local environment if data sensitivity matters; (3) confirm you have a Python runtime and review any command-line config files you pass in for secrets; (4) if you need networked benchmarking, verify the scripts do not call external endpoints (no network calls were observed in the provided snippets). If you want extra assurance, request the full untruncated scripts for a line-by-line review or run them in a sandbox/VM.
Review Dimensions
- Purpose & Capability
- okName/description (CHRO advisory: hiring, comp, org design) match the provided artifacts: SKILL.md, three reference docs, and two Python tools for headcount modeling and comp benchmarking. The included scripts implement the expected functionality (roster/plan JSON input, band lookups, cost/risk calculations) and there are no extra binaries or unrelated dependencies declared.
- Instruction Scope
- noteRuntime instructions tell the agent to run the provided Python scripts to build hiring plans and benchmark comp. The scripts load JSON config/roster files and operate on employee data (salaries, performance, equity, demographics). They do not appear to instruct reading arbitrary system files or environment secrets. Caution: the scripts process sensitive HR/PII (names, compensation, gender/ethnicity) which is expected for this tool but means users should avoid feeding real employee data to an untrusted environment or third-party agent without review/consent.
- Install Mechanism
- okNo install spec is present (instruction-only with shipping Python scripts). Nothing is downloaded or extracted; no external package installs are required by the skill package itself. Running the scripts requires a Python runtime, which is reasonable and proportional to the skill's purpose.
- Credentials
- okThe skill declares no required environment variables, no credentials, and no config paths. The scripts accept local JSON input files (roster/plan) which is appropriate for HR modeling. There are no indications the skill requests unrelated secrets or broad system-level access.
- Persistence & Privilege
- okFlags show always: false and normal agent invocation allowed. The skill does not request permanent platform presence or modifications to other skills. Autonomous invocation is permitted by default but is not combined with broad credential access or suspicious install behavior.