Back to skill

Security audit

Refundable Hotel

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent hotel-search helper, but it asks agents to install an unpinned global CLI and silently persist raw travel queries, which users should review before installing.

Install only if you trust the flyai CLI publisher and are comfortable with the agent using real-time third-party booking data. Prefer manual, reviewed installation in an isolated environment, and disable or avoid the execution log unless raw-query retention is clearly disclosed and controlled.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:9
Finding

Mandatory Third-Party Promotional Content and Booking-Link Injection

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:38
Finding

Unpinned Global Installation of an External npm Package

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
references/runbook.md:29
Finding

Undisclosed Persistence of Raw Queries and Unsafe Shell-Based Log Writing

Content
View full analysis
> .flyai-execution-log.json ``` ``` ### Technical Analysis The runbook directs the agent to retain the user’s complete raw query, command history, timing data, fallback activity, and result metadata in `.flyai-execution-log.json`. It states that the internal log is not shown to users, but it provides no consent mechanism, retention limit, redaction policy, file-permission requirement, or repository-ignore rule. Travel queries may reveal destinations, dates, budgets, accommodation requirements, and other personal planning information. Retaining the raw input creates unnecessary local exposure to other processes, users, backups, or accidental source-control commits. The proposed persistence command inserts gene ...[truncated 1803 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (4)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 135)May include surrounding context.

flyai search-hotel --dest-name "Beijing" --key-words "免费取消" --sort rate_desc --check-in-date 2026-05-01 --check-out-date 2026-05-02

text

## Output Rules

1. **Conclusion first** — lead with the key finding
2. **Comparison table** with ≥ 3 results when available

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The playbook hard-codes the query term "免费取消" in command examples, which imposes a specific language/locale behavior regardless of the user's language preference. The file does not state that this is region-specific or give users an opt-in choice for language, so it is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The runbook explicitly logs the raw user query (user_query: "{raw input}") and persists execution logs to a local file, but the document provides no notice, minimization, redaction, retention, or access-control guidance. In a travel-booking skill, raw queries can contain personal and trip-sensitive data such as names, destinations, dates, booking preferences, or even passport/visa details, so unnecessary retention increases privacy and compliance risk if logs are exposed or reused.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The fallback instructs users to run npm i -g @fly-ai/flyai-cli, which modifies the global system environment and executes code from a package registry without any warning, isolation guidance, or trust verification. In an agent skill context, this can lead to unnecessary privilege use, environment drift, or supply-chain exposure if the package is compromised or the instruction is followed automatically.

Content

No source excerpt is available for this finding.