Back to skill
Skillv1.0.0
ClawScan security
Mercado Pago · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 11:05 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only, informational skill about Mercado Pago that does not request credentials, install code, or perform system/network actions — its declared contents match its purpose.
- Guidance
- This skill is an informational reference card about Mercado Pago and appears internally consistent and low-risk. Before installing, consider that the skill's source and homepage are not provided — while the current version is instruction-only, skills can be updated later. If you prefer to limit automatic use, keep autonomous invocation disabled for agents or only allow the skill when you explicitly invoke it. If you need higher assurance, install only skills from publishers you recognize or with a documented homepage/source.
Review Dimensions
- Purpose & Capability
- okThe skill name, description, and SKILL.md all describe an informational profile of Mercado Pago. There are no unrelated requirements (no env vars, binaries, or config paths) that would be inconsistent with an informational reference card.
- Instruction Scope
- okSKILL.md contains only company overview content and a small 'read_when' trigger list indicating when the agent should use this content. It does not instruct the agent to read files, access environment variables, call external endpoints, or collect/transmit user data.
- Install Mechanism
- okNo install spec and no code files are present, so nothing will be written to disk or installed — lowest-risk model for a skill.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. There is no apparent need for secrets or external service keys for the stated purpose.
- Persistence & Privilege
- okalways is false and there are no special persistence or system-modifying behaviors. The skill can be invoked by the model (default), which is normal for skills; this is not a concern here given the skill's informational nature.