Security Audit

ferminrp/agent-skills:skills/inflacion-argentina-ipc

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/inflacion-argentina-ipc 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 Command Injection via `jq` filter construction.

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	Command Injection via `jq` filter construction The skill's workflow explicitly states that user-requested periods will be used to filter data locally with `jq`. Specifically, step 4 mentions: 'Si el usuario pide periodo, filtrar localmente con `jq` por `fecha`.' If user input for dates or other filter criteria is directly interpolated into the `jq` command string without proper sanitization, a malicious user could inject arbitrary `jq` expressions or potentially shell commands. This could lead to data manipulation, denial of service, or arbitrary code execution within the agent's environment. Implement robust input sanitization and validation for any user-provided data used to construct `jq` filter expressions. To safely pass user-controlled values, consider using `jq`'s `--arg` or `--argjson` options, which treat inputs as literal strings or JSON values, preventing injection. Alternatively, parse the JSON response within the agent's native language and perform filtering programmatically, avoiding shell execution for user-controlled logic.	LLM	SKILL.md:45

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/9a1c66fd1b003f6e.svg)](https://skillshield.io/report/9a1c66fd1b003f6e)