Security Audit

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

github.com/dceoy/speckit-agent-skills

AI SkillCommit c21d8d2defd2

TRUSTED

Scanned 12 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 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Arbitrary Code Execution via Repository Script, Potential Command Injection Guidance.

The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, dependency_graph, static_code_analysis. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 8, 2026 (commit c21d8d2d). 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

78%

Behavioral Risk Signals

Shell Execution

2 findings

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Arbitrary Code Execution via Repository Script The skill instructs the agent to execute a bash script (`.specify/scripts/bash/check-prerequisites.sh`) located in the repository root. If the repository being analyzed is malicious or compromised, this script could contain arbitrary code that will be executed by the agent's host environment. Do not execute scripts found in the target repository. Implement the logic of the prerequisite check within the skill's trusted code (e.g., using Python or internal tool functions) to verify file existence and structure safely.	Unknown	SKILL.md:32
MEDIUM	Potential Command Injection Guidance The skill provides specific instructions on escaping quotes for shell arguments (`e.g 'I'\''m Groot'`). This suggests the agent is expected to construct shell commands dynamically using inputs (like user focus areas). Constructing shell commands via string manipulation is prone to injection vulnerabilities if user input is not perfectly sanitized. Remove instructions that encourage shell command construction. Explicitly instruct the agent to use safer alternatives like `subprocess.run` with argument lists (if Python is available) or dedicated file reading tools that do not involve shell interpretation.	Unknown	SKILL.md:38

Scan History

Embed Code

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