Security audit

Outlit Cli

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for Outlit CLI use, but it asks users to install and configure a powerful customer-data CLI with too little scoping and safety guidance.

Review this before installing if the CLI would access real customer records or analytics. Prefer a pinned, trusted CLI version, avoid broad `setup --yes` unless you want all detected agents configured, and only run customer or SQL queries when you are authorized and can limit or redact sensitive output.

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 (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:8
Finding: Unpinned Global Installation of a Third-Party CLI Package
Content: View full analysis
Remediation: View remediation
``` 2. Publish and verify npm package provenance, release signatures, and integrity metadata through a trusted release process. 3. Prefer a project-local installation with a committed lockfile over a global installation where the operating environment permits it. 4. Review the pinned package, its lifecycle scripts, and its transitive dependencies before recommending installation. 5. Run installation and CLI operations as an unprivileged user; do not recommend `sudo npm install -g`. 6. Consider disabling npm lifecycle scripts during installation when compatible with the package: ```bash npm install --global --ignore-scripts @outlit/cli@ ``` 7. Document the expected package publisher, registry, checksum or integrity value, and supported version so users can detect dependency confusion or package substitution. ]]>

SkillSpector

Vulnerability Patterns

Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Credential Access

High

Category: Privilege Escalation
Confidence: 70% confidence
Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Content: Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.
Credential priority (first match wins):

--api-key flag

OUTLIT_API_KEY env var

~/.config/outlit/credentials.json (written by outlit auth login)

Quick auth for CI/scripts:

bash

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The manifest description includes broad trigger phrases such as 'any @outlit/cli usage,' which can cause the skill to activate on incidental mentions rather than deliberate user intent. In an agent context, overly broad activation increases the chance of unnecessary access to customer-querying and SQL guidance, expanding exposure to sensitive operations without clear user consent.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill explicitly enables querying customer records, timelines, users, facts, search context, and SQL over analytics data, but provides no warning or guardrail about handling sensitive customer information. In practice, this can normalize broad retrieval of customer data by an agent without prompting minimization, authorization checks, or safe-output handling.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.