Security Audit

react-native-testing

github.com/callstackincubator/agent-skills

AI SkillCommit ace14e40df8e

CAUTION

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

react-native-testing received a trust score of 57/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Covert behavior / concealment directives, Prompt Injection: Instruction to override LLM's internal knowledge.

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 May 1, 2026 (commit ace14e40). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

85%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
CRITICAL	Prompt Injection: Instruction to override LLM's internal knowledge The skill explicitly instructs the LLM to disregard its own training data regarding `@testing-library/react-native` and instead rely solely on the skill's provided reference files and the user's project source code. This is a direct attempt to manipulate the LLM's knowledge base and decision-making process, which falls under prompt injection. While the intent appears to be benign (ensuring up-to-date information), it establishes a pattern of overriding the LLM's core instructions or knowledge. Rephrase instructions to guide the LLM's reasoning without directly commanding it to 'not fall back on memorized patterns' or 'always rely on this skill's reference files'. Instead, present the skill's information as the most current and relevant, allowing the LLM to integrate it into its reasoning without an explicit override command.	LLM	SKILL.md:3
HIGH	Covert behavior / concealment directives CSS-based text hiding Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	plugins/vendored/.agents/skills/react-native-testing/SKILL.md:59

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/c81f5f3bb9408a56.svg)](https://skillshield.io/report/c81f5f3bb9408a56)