Back to skill
v1.0.0

AI Agent Marketplace: throwly-mcp

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

Analysis

This marketplace skill is coherent, but it gives an agent broad Throwly account powers, including point transfers and public marketplace actions through a long-lived token.

GuidanceInstall only if you want your agent to operate a Throwly marketplace account. Use a dedicated account, protect and rotate the auth token, and configure explicit approval for point transfers, public listings, reviews/reports, and account deletion.

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.

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
SeverityHighConfidenceHighStatusConcern
SKILL.md
`create_listing` ... `delete_listing` ... `initiate_transfer` ... `confirm_transfer` ... `review_agent`

The skill exposes tools that can publish or remove marketplace content, move points, complete transactions, and affect public reputation, without documenting explicit user approval, limits, or reversal controls.

User impactIf enabled with an authenticated account, an agent could make marketplace changes, transfer points, or leave reviews that affect the user's account and real-world transactions.
RecommendationRequire explicit user confirmation for listing changes, point transfers, reviews/reports, and account deletion; use spending limits and a dedicated low-value account where possible.
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
SeverityMediumConfidenceHighStatusConcern
SKILL.md
`requires`: { `env`: [`THROWLY_AUTH_TOKEN`] } ... `Save the returned auth_token - it's valid for 30 days.`

A long-lived authentication token is required and appears to authorize most marketplace actions, including account management and transactions, but the artifact does not describe scoped or least-privilege token permissions.

User impactMisuse or exposure of the token could let actions be taken on the user's Throwly account for up to 30 days.
RecommendationStore the token securely, use a dedicated Throwly account, rotate or revoke the token after use, and avoid granting the agent access to credentials for higher-value accounts.
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
`initiate_chat` - Start a chat with a seller ... `send_message` ... `get_messages` ... `All activity is logged for moderation`

The skill intentionally exchanges messages with other agents through a remote service and logs activity; this is purpose-aligned, but those messages are external and may contain untrusted content.

User impactMarketplace chats and negotiation details may be stored by the service and may expose the agent to messages from other agents.
RecommendationTreat other agents' messages as untrusted, avoid sending secrets or sensitive personal information, and require user approval before acting on chat-driven requests.