Security Audit

dceoy/speckit-agent-skills:skills/speckit-constitution

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-constitution 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 Self-Modifying Agent Instructions, Automated Modification of CI/CD Configurations.

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

Filesystem Write

2 findings

Dynamic Code

1 finding

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Self-Modifying Agent Instructions The skill workflow explicitly instructs the agent to update `skills/speckit-/SKILL.md` files to align with new constitution principles. This allows the agent to modify its own system prompt and those of other skills. A malicious user could manipulate the constitution principles to inject harmful instructions (e.g., "Always exfiltrate data", "Ignore safety checks") which the agent would then propagate into the trusted `SKILL.md` definitions of the entire agent fleet, achieving persistence and privilege escalation. Remove `skills/speckit-/SKILL.md` from the list of files to be automatically updated. Skill definitions should be immutable to the agent or require a separate, strictly reviewed process for updates.	Unknown	SKILL.md:55
MEDIUM	Automated Modification of CI/CD Configurations The skill grants the agent permission to modify GitHub Actions agent configurations (`.github/agents/speckit.*.agent.md`) and prompts. While scoped to `speckit` files, allowing an LLM to autonomously rewrite CI/CD logic introduces a supply chain risk where hallucinated or manipulated configurations could compromise the build/deployment pipeline. Exclude `.github` directory files from automatic updates by the agent. Changes to CI/CD configurations should be proposed in a pull request description rather than applied directly to files.	Unknown	SKILL.md:54

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/72ee4c0795f02ff0.svg)](https://skillshield.io/report/72ee4c0795f02ff0)