Security audit

Basic Masonry

Security checks for vulnerabilities and agentic risk

Overview

This is a masonry guidance skill with no embedded executable code, but users should treat the installation command and physical safety guidance carefully.

Before installing, consider using a trusted or pinned ClawHub CLI if your environment supports it. Before acting on the masonry advice, check local permits and codes, use appropriate PPE for dust and chipping, and involve a structural engineer or licensed contractor for foundations, structural cracks, retaining walls over about 4 feet, or work near buildings.

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:15
Finding: Unpinned npm CLI Execution Through npx
Content: View full analysis
Remediation: View remediation
install howtousehumans/basic-masonry" ``` 2. Prefer an exact version rather than a range or mutable tag such as `latest`. 3. Use a lockfile and npm integrity metadata where the installation workflow supports them. 4. Document the expected package registry and trusted publisher so package resolution cannot silently use an unintended source. 5. Verify package provenance or signatures before execution where supported by the distribution platform. 6. For stronger isolation, require installation of a separately verified CLI and run it in a restricted environment with only the filesystem access required for Skill installation. 7. Periodically review the pinned release before updating it, rather than automatically consuming newly published versions. ]]>

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Rp1

Medium

Category: MCP Rug Pull
Confidence: 89% confidence
Finding: The install command invokes npx clawhub without pinning an exact package version, which can cause consumers to fetch whatever version is current at execution time. If the package is compromised, updated with unsafe behavior, or subject to dependency confusion/supply-chain abuse, installation could execute unintended code in the user's environment.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill gives detailed operational instructions for structurally significant and injury-prone work before presenting an upfront safety warning. In this context, users may begin acting on guidance involving heavy materials, silica dust, foundations, retaining walls, and code-sensitive structures without first being clearly warned about permit, collapse, and personal safety hazards.
Content: No source excerpt is available for this finding.