Security Audit
saga-orchestration
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
saga-orchestration received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Untrusted instruction to open local file.
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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Untrusted instruction to open local file The skill's instructions, provided within the untrusted input, contain a directive for the host LLM to 'open `resources/implementation-playbook.md`'. This is an instruction originating from untrusted content that attempts to manipulate the host LLM into performing a file system operation. If the LLM has access to the local file system, following this instruction could lead to unauthorized file access, potentially exposing sensitive information or allowing the LLM to read arbitrary files if the path can be manipulated. This also implies an excessive permission for the LLM to access local files. Remove or rephrase instructions that direct the host LLM to perform file system operations. If file access is necessary, ensure it is done through a controlled, sandboxed, and permission-restricted tool call, not via direct LLM instruction from untrusted content. | LLM | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/24829257f3ab1e0b)
Powered by SkillShield