Security Audit

ferminrp/agent-skills:skills/cotizaciones-pix-comparapix

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/cotizaciones-pix-comparapix 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 `curl` and `jq`.

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

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via `curl` and `jq` The skill's workflow explicitly states it will use `curl` to fetch data and `jq` to filter and process it. Specifically, steps 2, 3, 4, and 5 of the 'Workflow' section describe executing shell commands (`curl`, `jq`). If user-provided input (e.g., `symbol`, `isPix`, sorting criteria) is directly interpolated into the `jq` filters or `curl` parameters without proper sanitization or escaping, an attacker could inject arbitrary shell commands. For example, manipulating the `symbol` parameter in a `jq` filter like `select(.symbol=="BRLARS")` could lead to `jq` filter injection or even full command injection if the `jq` command is part of a larger shell pipeline. Ensure all user-provided input used in constructing `curl` commands or `jq` filters is strictly validated and properly escaped. Prefer using a dedicated HTTP client library and a JSON parsing library in the agent's native language (e.g., Python's `requests` and `json` modules) instead of shell commands (`curl`, `jq`) to minimize the attack surface for command injection. If shell commands are unavoidable, use parameterized execution or robust escaping mechanisms.	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/de51e8b3139a33f0.svg)](https://skillshield.io/report/de51e8b3139a33f0)