Security audit

Magic Need

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently records an agent's missing tool or data needs in a local JSON file, with no evidence of hidden execution, network exfiltration, or privilege abuse.

Install only if you are comfortable with agents writing unmet-tool descriptions to ~/.magic-need/needs.json. Do not record secrets, tokens, personal data, incident details, or confidential system names unless that local retention and any later reports are acceptable.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.
md
node scripts/cli.js list

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.
md
node scripts/cli.js list

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.
md
node scripts/cli.js list

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 126)May include surrounding context.
md
node scripts/cli.js list

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The README documents a clear command that archives resolved needs, but provides no warning that it changes or removes persisted data in ~/.magic-need/needs.json. In an agent-facing skill, undocumented destructive behavior increases the chance of accidental invocation by users or agents, leading to unintended data loss or loss of audit/history.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger description is broad enough to activate whenever an agent lacks any tool, API, or data source, which is a very common condition during normal task execution. That can cause over-invocation and unnecessary recording of agent reasoning, including speculative requests or sensitive context, expanding the skill’s data collection surface beyond a narrowly scoped use case.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill explicitly stores free-form need descriptions in a persistent local JSON file but does not warn that those descriptions may contain sensitive operational details, internal system names, missing security controls, or investigative leads. In this context, agents are encouraged to log unmet access needs during live tasks, making it plausible that secrets-adjacent or confidential environment details will be retained on disk and later exposed to other local users, tools, backups, or reports.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The CLI persistently stores arbitrary user- or agent-supplied descriptions to ~/.magic-need/needs.json without any notice, consent flow, minimization, retention limit, or redaction. In this skill's context, agents are specifically encouraged to record missing tools, APIs, logs, and data sources, which makes it reasonably likely that operators will enter sensitive internal details, credentials-adjacent information, incident context, or references to regulated data that then remain on disk indefinitely.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.