Security audit

Life State

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent wellness-tracking purpose, but its broad auto-triggers and Bash-based handling of free-form personal notes create privacy and command-execution risks that should be reviewed before use.

Review this skill before installing. It is not clearly malicious, but use it only if you are comfortable storing mood, sleep, soreness, and notes as plaintext JSON under your home directory for other skills to read. Avoid using it on shared machines or synced folders unless that is intended. Agents should invoke `life-state` with structured arguments rather than by concatenating free-form user text into Bash commands, and users should prefer explicit check-in commands over broad conversational triggers.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:36
Finding: Potential Shell Command Injection Through Unsafely Interpolated User Input
Content: View full analysis
` — `great | good | normal | tired | terrible` (freeform accepted; lowercased) - `--energy ` — 1-10 (rejected outside that range) ``` The instructions later explicitly direct the agent to derive free-form command arguments from natural-language input: ```markdown - **Parse loosely from natural language.** "feeling tired, energy 4" → `--mood tired --energy 4`. "sore chest and triceps" → `--sore chest,triceps`. - **Merge, don't replace.** If user adds "energy 6 now" later in the day, only update `--energy`. Don't wipe morning mood. - **Recommend the enum values** when you summarize back, but accept freeform — if a user says "drained" or "wired," store it verbatim; downstream skills can pattern-match or pass-through. ``` ### Technical Analysis The Skill instructs an agent to invoke the `life-state` CLI through Bash while deriving arguments from user-controlled natural-language input. Several arguments, including `--mood`, `--sleep`, `--sore`, and `--note`, can contain free-form text. The documentation does not require structured process invocation, argument arrays, validation, or shell-safe escaping. If an implementing agent constructs a command by directly substituting a user value into the documented Bash command, quotation marks, command substitutions, or shell metacharacters in that value can terminate the intended argument and introduce additional shell operations. For example, a malicious note containing syntax ...[truncated 2302 chars]
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 (5)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The README explicitly states that daily mood, energy, soreness, sleep quality, and notes are stored persistently in plaintext JSON under the user's home directory, but it does not warn that this is sensitive personal data or discuss local access/privacy implications. In the context of a personal-AI memory framework designed for other skills and agents to read directly, this increases the chance that users unknowingly retain and expose health-adjacent data to other local tools, backups, sync systems, or shared-machine users.
Content: No source excerpt is available for this finding.

Shadow Command Trigger

Medium

Category: Trigger Abuse
Confidence: 84% confidence
Finding: The trigger 'log mood' overlaps with the built-in command namespace around 'log', creating a shadow-command condition where the skill may intercept requests intended for core logging functionality. In context, that misrouting can lead to accidental recording of sensitive wellness information or prevent the intended built-in command from running.
Content: No source excerpt is available for this finding.

Shadow Command Trigger

Medium

Category: Trigger Abuse
Confidence: 84% confidence
Finding: The trigger 'log energy' similarly conflicts with the built-in 'log' command family and can cause the skill to be invoked when the user intended a core logging action. Given that this skill writes persisted state, the collision increases the chance of unintended capture and storage of personal wellness information.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger set includes broad natural-language phrases such as 'I feel', 'energy is', and 'today I am' that are likely to match ordinary conversation and cause the skill to activate unexpectedly. In this skill, unexpected activation is more sensitive because it captures and persists wellness data, so users may disclose mood, sleep, or soreness information without realizing it will be stored.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly stores daily mood, energy, soreness, sleep quality, and free-text notes in a persistent local directory, but it does not warn the user about retention, location, or downstream access by other skills. Because these are sensitive wellness signals and notes may contain additional health details, silent persistence creates privacy and consent risks even if storage is only local.
Content: No source excerpt is available for this finding.