Structs Reconnaissance
Analysis
This is a disclosed, instruction-only Structs game reconnaissance workflow, but it uses broad read queries and writes persistent intel notes that users should review.
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.
all reconnaissance queries can be done in **< 1 second** via PostgreSQL instead of CLI. This is essential for combat automation, real-time threat monitoring, and galaxy-wide scouting.
The skill encourages broad and fast local database querying for game reconnaissance. This is aligned with the stated purpose, but users should understand it may enumerate large portions of game state.
All via `structsd query structs [subcommand] [args]`
The workflow depends on an external structsd CLI, while the supplied metadata lists no required binaries and there is no install spec. This is a dependency/provenance notice, not evidence of unsafe behavior.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Persist intelligence — After gathering, update: ... memory/intel/players/{player-id}.md ... vulnerabilities, relationship ... memory/intel/threats.md — Threat board ranked by severityThe skill deliberately writes persistent dossiers and threat rankings that future agent sessions may reuse. This is disclosed and scoped to memory/intel, but stale or incorrect intel could affect later decisions.