Legal Advisor
Analysis
The skill appears to be a coherent legal-template helper with no evidence of credential use, data exfiltration, destructive actions, or hidden network behavior, though its runnable bash/Python helpers are under-declared in metadata.
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.
Required binaries (all must exist): none ... Install specifications: No install spec — this is an instruction-only skill.
The registry presents the skill as instruction-only with no binary requirements, but SKILL.md lists bash 4+ and python3 and the manifest includes executable shell scripts. This is not suspicious by itself, but the runtime expectations are under-declared.
#!/usr/bin/env bash ... python3 - "$CMD" "$QUERY" << 'PYEOF'
The skill includes executable shell code that launches inline Python. The visible behavior is purpose-aligned template generation and does not show unsafe downloads, eval, network calls, or destructive commands.