Back to skill
Skillv1.0.0
ClawScan security
Agentic Factory · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 15, 2026, 3:04 AM
- Verdict
- benign
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- The skill's instructions and requirements are internally consistent with an orchestration/orchestrator role and do not request extra credentials or installs, but the guidance is broad and depends on platform-level session-spawning primitives whose trustworthiness you should verify.
- Guidance
- This skill is internally coherent for orchestrating multi-agent software production and does not itself ask for secrets or install code. Before installing: (1) confirm the provenance — the skill's source is unknown; prefer skills from known authors or a verified registry; (2) verify what the platform commands sessions_spawn and spawn actually do and what privileges spawned sessions get (can they access files, network, or credentials?); (3) run the skill in a sandbox or dev account first and monitor logs; (4) avoid granting it access to production secrets or cloud credentials until you understand how spawned agents authenticate and what they can act on; (5) review the full, untruncated SKILL.md for any hidden or additional steps. If you can provide the platform binding for sessions_spawn/spawn or the skill's source, I can reassess with higher confidence.
Review Dimensions
- Purpose & Capability
- okName, description, and SKILL.md content consistently describe a multi-agent orchestration/orchestrator role. There are no required binaries, env vars, or install steps that are unrelated to the stated purpose.
- Instruction Scope
- noteInstructions focus on decomposing work and coordinating specialist agents (Architect, Builder, Reviewer) and include example commands (sessions_spawn, spawn). They do not instruct reading local files, environment variables, or exfiltrating data, but they give broad discretion to spawn and coordinate agents — this relies on platform APIs (sessions_spawn/spawn) whose behavior is unspecified.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill; nothing will be written to disk by the skill itself.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. The lack of requested secrets is proportionate, though runtime orchestration implicitly requires platform privileges to create sessions.
- Persistence & Privilege
- notealways:false and default autonomous invocation are appropriate for an orchestrator skill. Be aware that the skill's purpose is to spawn and coordinate agents — if the underlying platform grants those spawned sessions broad access, the effective blast radius increases (this is platform-level, not the skill requesting extra privileges).