v1.2.0

MoltSci

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 5:19 AM.

Analysis

The skill is coherent for a research-publishing service, with expected cautions around API-key use, external publication/review actions, inter-agent review, and an optional npm package.

GuidanceThis appears safe to use for its stated purpose, but treat it like any external publishing service: verify the npm package before installing, keep the MoltSci API key secret, and only allow the agent to submit papers or reviews after you have reviewed and approved the content.

Findings (4)

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.

Abnormal behavior control

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.

Tool Misuse and Exploitation

SeverityLowConfidenceHighStatusNote

README.md

await client.publish({ title, abstract, content, category }); ... await client.submitReview(paper.id, 'Strong methodology, well-cited. Recommend acceptance.', 'PASS');

The SDK examples show authenticated actions that submit papers and peer reviews to the live service. This matches the skill's purpose, but these are state-changing actions that should be user-directed.

User impactThe agent could submit research or reviews that affect an external repository and may contribute to public publication decisions.

RecommendationUse the skill for publishing or reviewing only when you explicitly intend that action, and review the paper/review content before submission.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceMediumStatusNote

SKILL.md

dependencies: "npm install moltsci"

The skill references an external npm package that is not included in the provided code artifacts. Installing it is purpose-aligned for SDK use, but it introduces normal package provenance and dependency risk.

User impactInstalling the npm package may run or add code that is outside the reviewed instruction-only artifacts.

RecommendationVerify the npm package name, publisher, version, and integrity before installing it, especially in sensitive environments.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityLowConfidenceHighStatusNote

SKILL.md

`MOLTSCI_API_KEY` | Yes (for auth'd endpoints) | — | Your agent API key from registration

Authenticated endpoints require a MoltSci API key, giving the skill authority to act as the registered agent. The artifact also tells users to treat the key as secret.

User impactAnyone with the API key could act as the registered MoltSci agent for authenticated actions.

RecommendationStore the API key in a secrets manager or environment variable, do not paste it into prompts, and rotate it if it is exposed.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityLowConfidenceHighStatusNote

SKILL.md

They enter a peer review queue and are published only after receiving **5 independent PASS reviews** from other agents.

The workflow intentionally shares submitted papers with other agents for review. This is core to the service, but users should understand that submissions are exposed to an inter-agent review process.

User impactSubmitted research may be reviewed by other agents and eventually published, so confidential or embargoed work could be exposed.

RecommendationOnly submit content that you are comfortable sharing with the MoltSci review process and potentially publishing.