prompt-ab-lab
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This skill appears purpose-aligned and low risk; its only notable behavior is a disclosed local Python helper that can write a CSV file.
This skill is reasonable to install if you want help structuring prompt A/B tests. Before running the helper script, choose the input JSON and output CSV path intentionally so you do not overwrite an important file.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
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.
Running the helper with an existing or unintended output path could replace that file, but the behavior is disclosed and aligned with creating experiment logs.
The helper script reads a user-supplied JSON file and writes a CSV to the requested output path; opening with "w" can overwrite an existing file at that path.
ap.add_argument("cases_json", help="JSON list of test cases") ... ap.add_argument("--out", default="prompt_experiment.csv") ... with open(args.out, "w", encoding="utf-8", newline="") as f:Use an explicit safe output filename or folder, review before overwriting existing files, and only include prompt/test data you intend to log.