Back to skill
Skillv1.0.0
ClawScan security
Al Brooks Price Action · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 7, 2026, 4:05 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only trading-analysis skill whose files, references, and runtime directions are consistent with its stated purpose and do not request unexpected system access or credentials.
- Guidance
- This skill appears coherent and low-risk: it is documentation-driven and asks for no credentials or installs. Before using, consider: (1) only supply charts/screenshots that don’t contain private data you’d rather not share; (2) if you prefer the agent not to call this skill unless you explicitly request it, ask the platform to disable implicit invocation for this skill; and (3) treat trading recommendations as discretionary advice — verify any trade plan independently.
Review Dimensions
- Purpose & Capability
- okName, description, and included reference files all align: the skill is explicitly a Brooks-style discretionary price-action analysis tool. It requests no binaries, env vars, or config paths, which is proportionate for an instruction-only analyzer.
- Instruction Scope
- okSKILL.md limits activity to reading the shipped reference documents and user-provided inputs (OHLC text, tables, screenshots, notes). It explicitly warns against hallucinating unreadable values and does not instruct the agent to read unrelated system files or transmit data externally.
- Install Mechanism
- okNo install spec and no code files are provided (instruction-only). Nothing will be downloaded or installed on the host as part of this skill.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. There are no requests for unrelated or excessive secrets.
- Persistence & Privilege
- notealways:false and user-invocable:true (normal). The agents/openai.yaml sets policy.allow_implicit_invocation: true, so the agent may choose to invoke the skill implicitly when it thinks the skill is relevant. This is not inherently dangerous for this skill but is a behavioral property the user should be aware of.