Security audit

mempool.space Public API

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent read-only mempool.space API helper, but its setup uses a mutable remote OpenAPI schema that can change after review.

Review the setup command before installing. Prefer linking UXC to the bundled local schema or a pinned commit with a verified hash, and avoid querying addresses, transactions, or Lightning identifiers you consider private through a public explorer service.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:42
Finding: Mutable Remote OpenAPI Schema Creates a Supply-Chain Risk
Content: View full analysis
Remediation: View remediation
/skills/mempool-space-openapi-skill/references/mempool-space-public.openapi.json ``` 3. Publish an expected SHA-256 digest and verify the downloaded schema before passing it to UXC. Fail closed if verification does not succeed. 4. Extend `scripts/validate.sh` to reject mutable schema references such as `/main/` and verify that the documented remote schema URL contains an approved commit hash. 5. Validate the effective runtime schema before linking. Enforce an allowlist of the expected server, GET-only HTTP methods, and documented paths. 6. Store the verified schema locally and link from that local copy so later upstream modifications cannot silently change an existing installation. ]]>

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This file is a JSON OpenAPI manifest, so SQP-1 applies. Several user-supplied parameters such as address, txid, public_key, short_id, and searchText are defined only as generic strings, and the spec does not document expected formats, scope limits, or exclusion conditions; this can lead to overly broad invocation behavior in tools that auto-generate skill interfaces from the manifest.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The usage examples instruct the user to run commands that connect to the public mempool.space API, but they do not explicitly warn that doing so sends requests and query data to a third-party service. This is primarily a transparency and privacy issue: users may unintentionally disclose addresses, transaction IDs, node IDs, or usage metadata to an external operator when following the examples.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.