Security audit

Survival Basics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent home repair, plumbing, and cooking guide with some ordinary privacy and install-supply-chain cautions, but no evidence of deception or harmful behavior.

Before installing, use a trusted or pinned installer where possible, and avoid letting the skill permanently store household locations, budget details, dietary restrictions, or food-insecurity information unless you want that remembered.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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 (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:15
Finding: Unpinned Package Execution Through npx
Content: View full analysis
Remediation: View remediation
install survival-basics" ``` 2. Use a lockfile and verify package integrity through the package manager's supported integrity metadata. 3. Configure and document the expected trusted registry rather than relying on ambient registry configuration. 4. Review the pinned package and its transitive dependencies before publication. 5. Prefer a locally installed, verified installer over automatically downloading and executing the latest remotely resolved package. 6. Run installation with the least-privileged account possible and without unnecessary secrets in the environment. 7. Establish an update process in which new package versions are audited before the pinned version is changed. ]]>

other

Note

Location: SKILL.md:566
Finding: Unbounded Cross-Session Retention of Household and Personal-Vulnerability Data
Content: View full analysis
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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The phrase "Use when someone needs practical self-sufficiency skills for home and food" is very broad and not tied to specific trigger phrases or exclusion conditions. Because "practical self-sufficiency" can cover many everyday requests, this may cause the skill to be invoked outside its intended repair/plumbing/cooking scope.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 91% confidence
Finding: The install command invokes npx clawhub install survival-basics without pinning a specific package version. That allows the fetched package or transitive behavior to change over time, creating a supply-chain risk where a later malicious or compromised release could be executed in the user's environment.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: Items like "Wants to eat well on a tight budget" and "New homeowner or renter who's never fixed anything" are common situations rather than specific activation criteria. Without explicit limits or negative examples, the skill could be selected for a wide range of generic food, budgeting, or home questions.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.