Skill Updater
Analysis
The skill coherently automates a user-requested skill release, but it can run a repository release script that publishes a new version, so users should only use it with a trusted repository.
Findings (2)
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Execute Release Script: It will locate the `scripts/release.sh` script in the repository and execute it with the provided arguments. This triggers the `publish.yml` GitHub Actions workflow
The skill explicitly directs the agent to execute a release script that can trigger publishing. This is expected for the skill's purpose, but it is a high-impact action.
RELEASE_SCRIPT="$REPO_PATH/scripts/release.sh" ... bash "$RELEASE_SCRIPT" "$SKILL_NAME" "$NEW_VERSION" "$CHANGELOG"
The actual release logic comes from a script inside the user-specified repository, not from the reviewed skill package. That is normal for this workflow, but it means the repository script's provenance matters.
