Security audit

Parent.skill

Security checks for vulnerabilities and agentic risk

Overview

This is a local parenting tracker whose sensitive family records are disclosed as plain local files, with no evidence of hidden execution or data transmission.

Install only if you are comfortable keeping baby and caregiver observations in readable local files on this device. Protect the user account, backups, and any shared computer access, and remove ~/.parent-skill/children/ when you no longer want the records retained.

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

Warning

Location: SKILL.md:48
Finding: Unencrypted Storage of Sensitive Child and Caregiver Data
Content: View full analysis
Born: [YYYY-MM-DD] > Current Age: [auto-calculated] > Last Updated: [YYYY-MM-DD] --- ## Identity - **Name:** - **Date of birth:** - **Birth weight/length:** ## Feeding Patterns - **Method:** (breast / bottle / combo / solids started) - **Average interval:** - **Usual amounts:** - **New foods tried + reactions:** ## Sleep Patterns - **Average wake window:** - **Nap schedule:** - **Night sleep pattern:** - **What helps fall asleep:** - **Longest stretch:** ## Soothing Playbook | Method | Success Rate | Notes | |--------|-------------|-------| | | /10 attempts | | | | /10 attempts | | | | /10 attempts | | ## Cry Patterns - **Hungry cry:** - **Tired cry:** - **Gas/discomfort cry:** - **Bored/overstimulated:** ## Milestones | Date | Milestone | Context | |------|-----------|---------| | | | | ## Caregivers | Person | Role | Special Notes | |--------|------|---------------| | | Mom | | | | Dad | | | | | | ``` `templates/DAILY-LOG.md:3-25`: ```markdown > Storage: `~/.parent-skill/children/[name]/daily-log.jsonl` ## Entry Format ```json { "date": "YYYY-MM-DD", ...[truncated 3561 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High

Category: YARA Match
Confidence: 80% confidence
Finding: YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
Content: Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.
md
--- name: parent-skill description: "Unified parenting co-pilot for both parents. Track your baby's patterns together — feeding, sleep, milestones, soothing playbook. One source of truth for mom, dad, grandparents, and caregivers. Self-learning. Not medical advice." --- # parent.skill 👨‍👩‍👧 ## Purpose Parenting is a two-player game but most tools only talk to one parent. parent.skill is a shared parenting co-pilot — one baby profile, one source of truth, accessible to everyone who helps raise your child. No more "did she eat?" texts. No more "what time was her last nap?" calls. Everyone asks the

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The Logging Mode trigger is defined as any parent-reported observation, which is broad enough to capture ordinary conversation and cause unintended writes to persistent storage. In a shared caregiving context, accidental logging can corrupt the child profile, create misleading histories, and amplify privacy risk because sensitive family statements may be stored without clear user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The Query Mode trigger is described generically as a parent asking a question, without boundaries on which questions are in-scope or how to distinguish them from other conversational content. In a multi-user shared profile, this can expose stored child and caregiver data too easily, increasing the chance of unintended disclosure to someone with access to the session or to responses generated from ambiguous prompts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The Briefing Mode trigger activates on broad summary requests like 'how was her day?' or 'what did I miss?', which can be invoked accidentally or by an unintended party in a shared environment. Because the summaries aggregate recent sensitive observations, an overbroad trigger raises the likelihood of bulk disclosure of private family data rather than a single record lookup.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.