Antibody Humanizer
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill appears to be a local antibody-sequence analysis helper, with no artifact-backed evidence of exfiltration, persistence, credential use, or destructive behavior.
This looks reasonable for local bioinformatics use. Before installing or invoking it, review any Bash command or file write the agent proposes, and avoid placing confidential antibody sequences in shared or untrusted workspaces unless you are comfortable with local processing there.
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.
If invoked, the agent may be able to run local commands and modify files while performing the antibody humanization workflow.
The skill grants the agent local file and shell tools. This is disclosed and appears purpose-aligned for running the bundled local analysis script and writing results, but it is broader authority than a purely read-only instruction skill.
allowed-tools: [Read, Write, Bash, Edit]
Use the skill in a trusted project folder and review any proposed shell commands or file edits before allowing them.