Trust Assessment
food-cal-order received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Prompt Injection into Sub-Agents via Calendar Event Data.
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 | |
|---|---|---|---|---|
| CRITICAL | Prompt Injection into Sub-Agents via Calendar Event Data The skill explicitly instructs the parsing of untrusted input from calendar event titles and descriptions (e.g., service, restaurant, items, allergies, delivery notes). These parsed values are then directly embedded into the `task` prompts for sub-agents spawned via `sessions_spawn`. A malicious calendar event could craft its title or description to include prompt injection payloads, which would then be executed by the sub-agent. Since sub-agents are instructed to perform browser automation using a Chrome profile with saved login and payment information, a successful prompt injection could lead to unauthorized actions such as exfiltrating credentials, placing fraudulent orders, or navigating to malicious websites, potentially overriding critical safety instructions. Implement robust input validation and sanitization for all data extracted from calendar event titles and descriptions before embedding them into sub-agent prompts. Consider using structured data formats (e.g., JSON) for passing parameters to sub-agents instead of direct string interpolation. Additionally, implement explicit, hard-coded guardrails within the sub-agent prompts to prevent overriding critical safety instructions, especially concerning financial transactions and credential handling. | LLM | SKILL.md:100 |
Scan History
Embed Code
[](https://skillshield.io/report/4714691b5e44fa8a)
Powered by SkillShield