Security audit

clawr.ing

Security checks for vulnerabilities and agentic risk

Overview

This calling skill is understandable in purpose, but it relies on mutable remote API instructions and stores phone numbers in a local plaintext memory file without clear privacy controls.

Review the remote API documentation source and only use this skill if you trust clawr.ing with your API key, phone numbers, call content, and quota. Before installing, consider whether local plaintext contact storage is acceptable, and avoid saving third-party numbers unless you have authorization and a way to delete or protect the memory file.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Error

Location: SKILL.md:25
Finding: Mutable Remote Instructions Can Influence Agent Call Behavior
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:29
Finding: Phone Numbers and Calling Preferences Are Persisted in Plaintext
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill directs the agent to create and maintain a local memory file containing phone numbers and user/contact preferences, which are sensitive personal data, but provides no retention limits, consent guidance beyond operational use, access controls, minimization rules, or warning about privacy implications. In an agent environment, this can lead to unnecessary collection and persistence of third-party contact data and increase the risk of leakage, misuse, or noncompliant handling of personal information.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.