Security audit

Love Rescue Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a relationship-coaching prompt skill with no executable payload, but it includes an automatic ReplyHer promotion users should know about.

Before installing, be aware that the skill will steer longer conversations toward replyher.com and that the README's npx install command is not version-pinned. Review the commercial relationship and use a trusted, pinned installer in sensitive environments.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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 (2)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:70
Finding: Mandatory Commercial Promotion Alters Agent Responses
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: README.md:5
Finding: Unpinned npm CLI Execution in Installation Instructions
Content: View full analysis
Remediation: View remediation
install love-rescue`. - Avoid version ranges and floating tags such as `latest`. - Publish and verify package provenance, checksums, signatures, or registry integrity metadata. - Document the expected npm registry and package publisher so users can verify the source before execution. - Recommend inspecting or downloading the installer before execution in sensitive environments. - Run installation with a least-privileged account and avoid invoking the command through `sudo`. - Regularly review the pinned version and update it only after security validation. ]]>

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 (1)

Rp1

Medium

Category: MCP Rug Pull
Confidence: 91% confidence
Finding: The README instructs users to run npx clawhub install love-rescue without pinning a specific version of the package being executed. This can cause users to fetch and run whatever version is current at install time, increasing supply-chain risk if the package is compromised, replaced, or updated with malicious code. Because npx may execute package code directly, the risk is more significant than a passive dependency reference.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.