Security audit

Knot Tying Rope Work

Security checks for vulnerabilities and agentic risk

Overview

The skill is mainly a normal knot-tying guide, but it asks for unnecessary filesystem authority and uses an unpinned npx install command.

Review before installing. The knot-tying instructions themselves look ordinary and include useful safety warnings, but install with least privilege, avoid running the unpinned npx command in privileged or secret-bearing environments, and prefer removing or tightly sandboxing filesystem access because this skill does not need it.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:15
Finding: Unpinned Package Execution During Skill Installation
Content: View full analysis
Remediation: View remediation
` reference. - Prefer an installation mechanism backed by a committed lockfile and reproducible dependency resolution. - Verify downloaded artifacts with cryptographic integrity hashes or signatures before execution. - Document the expected package registry and trusted publisher so alternate or attacker-controlled registries are not used silently. - Review package provenance and publish immutable, signed releases where supported. - Run installation with the lowest necessary privileges and avoid administrator or root execution. - In CI/CD, isolate installation in a restricted environment without production secrets until the artifact has been verified. ]]>

T05 · Unauthorized Access and Privilege Escalation

Note

Location: SKILL.md:12
Finding: Unnecessary Filesystem Capability Violates Least Privilege
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The invocation guidance says to use the skill when someone needs to "tie something down" or wants to learn a skill that "crosses every manual domain." Those phrases are broad and could overlap with many ordinary conversations, making it unclear when this skill should or should not activate.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 93% confidence
Finding: The install command invokes npx clawhub install knot-tying-rope-work without pinning a specific package version, which introduces supply-chain risk. If the referenced package or one of its dependencies is updated maliciously or unexpectedly, users could execute unreviewed code during installation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The activation guidance includes generic contexts like "hanging something heavy" and "repair," but does not define where the skill should stop applying or what related requests belong elsewhere. This ambiguity can cause unintended invocation for general DIY, hauling, or safety-critical tasks.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.