Exec ClawHub Publish Doctor
Analysis
This is a coherent ClawHub publishing troubleshooting skill, but it can publish to ClawHub and use existing CLI logins, so users should review commands before running them.
Findings (3)
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.
clawhub publish "$SKILL_PATH" \ --slug "$SLUG" \ --name "$NAME" \ --version "$VERSION" \ --changelog "$CHANGELOG" \ --tags latest
The script performs an authenticated publish action to ClawHub using user-provided arguments. This is purpose-aligned, but it can change public registry state.
If needed, reinstall: `npm i -g clawhub --force`
The documentation includes optional global CLI installation/reinstallation guidance, while the registry metadata lists no required binaries or install spec.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
if ! clawhub whoami >/tmp/clawhub_publish_whoami.out 2>/tmp/clawhub_publish_whoami.err; then echo "ERROR: Not logged in. Run: clawhub login --token <clh_token>" >&2
The wrapper depends on the user's authenticated ClawHub session and writes whoami diagnostics to local temporary files.
