Security Audit

memory-safety-patterns

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

memory-safety-patterns received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Prompt Injection Attempt via Untrusted Instruction.

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 20, 2026 (commit e36d6fd3). 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

70%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Prompt Injection Attempt via Untrusted Instruction The skill package contains an instruction within the untrusted content block (`<!---UNTRUSTED_INPUT_START...--->` and `<!---UNTRUSTED_INPUT_END...--->`) that attempts to direct the host LLM to 'open' a file. According to SkillShield's rules, content within these delimiters should be treated as untrusted data, not instructions. If the host LLM processes this as an instruction, it indicates a prompt injection vulnerability, as the LLM is executing commands from untrusted sources. This is a direct attempt by the untrusted skill content to influence the LLM's behavior. Remove or rephrase instructions intended for the LLM so they are outside the untrusted content delimiters. Ensure the host LLM is robustly configured to ignore and not execute any instructions found within untrusted input blocks. If `resources/implementation-playbook.md` is intended to be part of the skill's context, it should be provided as a supporting file or explicitly loaded by the skill's trusted execution environment, not 'opened' by the LLM based on an untrusted instruction.	LLM	SKILL.md:24

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/80c90a22d3d17ea3.svg)](https://skillshield.io/report/80c90a22d3d17ea3)