Security Audit

dceoy/speckit-agent-skills:skills/speckit-analyze

github.com/dceoy/speckit-agent-skills

AI SkillCommit a934d48ecf66

CAUTION

Scanned 6 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

dceoy/speckit-agent-skills:skills/speckit-analyze received a trust score of 70/100, 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 Direct Shell Script Execution.

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 April 1, 2026 (commit a934d48e). 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

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Direct Shell Script Execution The skill explicitly instructs the host LLM to execute a shell script (`.specify/scripts/bash/check-prerequisites.sh`). Executing arbitrary scripts from untrusted skill content poses a severe command injection risk, potentially allowing an attacker to run any command on the host system where the LLM operates. Even if the script is part of the skill's own repository, the LLM's execution environment might not be sufficiently sandboxed to prevent malicious actions. The LLM should not be instructed to directly execute shell scripts from untrusted skill content. If external processes are required, they should be invoked through a secure, sandboxed execution environment with strict allow-listing of commands and arguments, or by using a dedicated tool/API that abstracts away direct shell access. The functionality of `check-prerequisites.sh` should ideally be reimplemented within the LLM's secure execution environment or through a trusted, pre-approved tool.	LLM	SKILL.md:35

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/2309c2f358fd09ae.svg)](https://skillshield.io/report/2309c2f358fd09ae)