Security audit

Paw.skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local pet-memory journaling helper with disclosed local persistence and no evidence of hidden code, network access, or destructive behavior.

Install only if you are comfortable keeping personal pet memories in a persistent local folder. Do not rely on this for veterinary or medical decisions, and remove ~/.paw-skill/pets/ if you want the stored profiles deleted.

A.I.G

Vulnerability Patterns

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

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill metadata and description are very broad and emotionally framed, but they do not define clear activation boundaries, disallowed requests, or negative examples. In an agent setting, this can cause over-triggering or misuse outside the intended memorialization scope, especially when paired with persistent memory behavior such as 'always load pet profile before responding' and adding cross-session data.
Content: No source excerpt is available for this finding.