Trust Assessment
sage-offers received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via `sage_rpc` arguments.
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 13, 2026 (commit 13146e6a). 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 | Potential Command Injection via `sage_rpc` arguments The skill's examples demonstrate invoking `sage_rpc` with JSON payloads as string arguments in a shell context (e.g., `sage_rpc make_offer '{...}'`). If the agent constructs these JSON strings from untrusted user input without proper sanitization or escaping, a malicious user could inject arbitrary shell commands. For instance, injecting shell metacharacters into fields like `offer_id` could lead to command execution on the host system where `sage_rpc` is executed. The agent calling this skill should ensure that any user-provided input used to construct the JSON payload for `sage_rpc` calls is properly sanitized, escaped, or passed as separate arguments to avoid shell injection. Prefer using a dedicated RPC client library that handles argument serialization securely instead of direct shell command construction. | LLM | SKILL.md:100 |
Scan History
Embed Code
[](https://skillshield.io/report/a25796373aa128a2)
Powered by SkillShield