Security Audit

ferminrp/agent-skills:skills/travel-promos-argentina

github.com/ferminrp/agent-skills

AI SkillCommit 84b0da6385e2

TRUSTED

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

ferminrp/agent-skills:skills/travel-promos-argentina received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via `jq` filters.

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 84b0da63). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via `jq` filters The skill's workflow explicitly states that it will apply filters locally using `jq` based on user input for fields like `category`, `destinationCountry`, or text in `title`/`id`. If the user-provided filter criteria are directly interpolated into the `jq` command or expression without proper sanitization and quoting, it could lead to command injection, allowing an attacker to execute arbitrary commands on the host system. While `jq` itself is not a shell, improper handling of user input when constructing the `jq` command line or the `jq` filter expression can lead to shell injection or `jq` expression injection. Ensure all user-provided input used in `jq` filter expressions is strictly validated, sanitized, and properly quoted to prevent injection of malicious `jq` syntax or shell metacharacters. Consider using a `jq` library in the programming language of the agent rather than shelling out, or implement a robust allow-list for filter values to restrict possible inputs.	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/1543cf192e66c88f.svg)](https://skillshield.io/report/1543cf192e66c88f)