Security Audit

dceoy/speckit-agent-skills:skills/speckit-plan

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-plan received a trust score of 81/100, 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 Unsafe Shell Command Construction Instruction, Unsanitized Variable in Shell Command.

The analysis covered 4 layers: llm_behavioral_safety, manifest_analysis, static_code_analysis, dependency_graph. 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

Filesystem Write

1 finding

Shell Execution

2 findings

Dynamic Code

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unsafe Shell Command Construction Instruction The skill instructs the agent to execute shell scripts and manually handle argument escaping (specifically mentioning single quote escaping). This instruction encourages the agent to construct shell commands via string concatenation rather than using parameterized execution. If user inputs or file contents are passed as arguments using this manual escaping method, it creates a high risk of command injection. Modify the instructions to ensure the agent uses a tool or method that accepts arguments as a list (argv) rather than a raw shell string. Remove instructions regarding manual shell escaping.	Unknown	SKILL.md:16
MEDIUM	Unsanitized Variable in Shell Command The workflow instructs the agent to run a shell script with a variable `<agent_type>` directly in the command string. If `<agent_type>` is derived from user input or untrusted context without strict validation, it allows for command injection. Ensure `<agent_type>` is validated against an allowlist of known agent types before execution, or pass it as a separate argument in a parameterized system call.	Unknown	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/766f563556ed18ab.svg)](https://skillshield.io/report/766f563556ed18ab)