Travel Planner

• Outcome: Pass
• Latest audit: May 29, 2026 · 8:42 PM UTC
• Version: 1.0.0

Overview

This travel-planning skill uses local scripts and limited external lookups in ways that match its stated purpose.

Install in a virtual environment, consider pinning dependencies before production use, and remember that weather and currency commands send destination or currency queries to external API providers.

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill advertises executable scripts with file read/write and network behavior, but no permissions are declared. This creates a transparency and policy-enforcement gap: a host system or reviewer cannot accurately constrain the skill's access, and users may invoke functionality without understanding that local files and external APIs are involved.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests>=2.31.0
geopy>=2.4.0
python-dateutil>=2.8.0
jinja2>=3.1.0

• Confidence: 97% confidence
• Finding: The dependency is specified with a lower bound only (`requests>=2.31.0`), which allows future, unreviewed versions to be installed. This weakens supply-chain control and can unexpectedly introduce breaking changes or newly disclosed vulnerable releases into the environment.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests>=2.31.0
geopy>=2.4.0
python-dateutil>=2.8.0
jinja2>=3.1.0
pandas>=2.0.0

• Confidence: 96% confidence
• Finding: `geopy>=2.4.0` is unpinned, so builds are not reproducible and may silently pull newer releases that have not been tested or security-reviewed. This is a supply-chain hygiene issue rather than an immediate exploit by itself.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests>=2.31.0
geopy>=2.4.0
python-dateutil>=2.8.0
jinja2>=3.1.0
pandas>=2.0.0
openpyxl>=3.1.0

• Confidence: 96% confidence
• Finding: Using `python-dateutil>=2.8.0` permits any later version, making dependency resolution nondeterministic and increasing exposure to supply-chain risk. While not directly exploitable on its own, it reduces assurance that deployed environments match tested ones.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests>=2.31.0
geopy>=2.4.0
python-dateutil>=2.8.0
jinja2>=3.1.0
pandas>=2.0.0
openpyxl>=3.1.0

• Confidence: 98% confidence
• Finding: `jinja2>=3.1.0` is unpinned, allowing arbitrary later versions to be installed without review. Because Jinja2 is a templating engine with a history of security issues, weak version control increases risk if a bad or vulnerable release is introduced.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

geopy>=2.4.0
python-dateutil>=2.8.0
jinja2>=3.1.0
pandas>=2.0.0
openpyxl>=3.1.0

• Confidence: 96% confidence
• Finding: `pandas>=2.0.0` is not pinned, so environment builds may pull different versions over time. This creates reproducibility and supply-chain exposure issues, though the requirements file alone does not show direct exploitability.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

python-dateutil>=2.8.0
jinja2>=3.1.0
pandas>=2.0.0
openpyxl>=3.1.0

• Confidence: 96% confidence
• Finding: `openpyxl>=3.1.0` is unpinned, which permits unreviewed future versions and undermines deterministic builds. For a library that parses spreadsheet/XML data, disciplined version pinning is especially important for supply-chain and parser-security hygiene.

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.