Make Skill Template
AdvisoryAudited by Static analysis on May 12, 2026.
Overview
No suspicious patterns detected.
Findings (0)
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.
NoteHigh Confidence
ASI06: Memory and Context PoisoningWhat this means
A poorly written generated skill could be invoked later in unintended situations.
Why it was flagged
The skill creates persistent SKILL.md instructions and discovery metadata that can influence when an agent loads future skills.
Skill content
description is the PRIMARY mechanism for automatic skill discovery
Recommendation
Review any generated skill’s name, description, instructions, and optional scripts before enabling or committing it.