Security Audit

dkyazzentwatwa/chatgpt-skills:distance-calculator

github.com/dkyazzentwatwa/chatgpt-skills

AI SkillCommit d4bad33523ff

CAUTION

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

dkyazzentwatwa/chatgpt-skills:distance-calculator received a trust score of 66/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 3 findings: 0 critical, 2 high, 1 medium, and 0 low severity. Key findings include Unpinned Python dependency version, Arbitrary File Read via User-Controlled Path, Arbitrary File Write via User-Controlled Path.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 24, 2026 (commit d4bad335). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

93%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Filesystem Write

2 findings

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings3

Severity	Finding	Layer	Location
HIGH	Arbitrary File Read via User-Controlled Path The `from_csv` method in `DistanceCalculator` directly uses a user-provided `filepath` to open and read a CSV file. This allows an attacker to specify any path on the file system, potentially leading to data exfiltration by reading sensitive files (e.g., configuration files, user data, system files) that the skill's execution environment has access to. This is exposed via the `--input` argument in the CLI. Implement strict validation and sanitization for `filepath` arguments. Restrict file operations to a designated, sandboxed directory. Do not allow arbitrary file paths from untrusted input. If file access is necessary, ensure the agent's environment enforces strict access controls (e.g., chroot, containerization) and that the skill explicitly requests and justifies such permissions.	LLM	scripts/distance_calc.py:204
HIGH	Arbitrary File Write via User-Controlled Path The `matrix_to_csv` method in `DistanceCalculator` directly uses a user-provided `output` path to create and write a CSV file. This allows an attacker to specify any path on the file system, potentially leading to overwriting existing files, writing malicious content to arbitrary locations, or consuming disk space. This is exposed via the `--output` argument in the CLI. Implement strict validation and sanitization for `output` arguments. Restrict file operations to a designated, sandboxed directory. Do not allow arbitrary file paths from untrusted input. If file writing is necessary, ensure the agent's environment enforces strict access controls (e.g., chroot, containerization) and that the skill explicitly requests and justifies such permissions.	LLM	scripts/distance_calc.py:236
MEDIUM	Unpinned Python dependency version Requirement 'geopy>=2.4.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'.	Dependencies	distance-calculator/scripts/requirements.txt:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/f7e246a7c787ea08.svg)](https://skillshield.io/report/f7e246a7c787ea08)