Trust Assessment
langchain-email-agent received a trust score of 79/100, 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 Missing required field: name, Direct Prompt Injection via 'instructions' parameter.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Direct Prompt Injection via 'instructions' parameter The `instructions` parameter from the `SendEmailDto` is directly inserted into the system prompt of the LLM via `message.EMAIL_PROMPT(instructions)`. This allows an attacker to inject arbitrary instructions, potentially overriding the agent's intended behavior, changing its persona, or instructing it to ignore safety guidelines. While `humanInTheLoopMiddleware` is present for the `EmailTool` to require approval before sending, this only mitigates the final action. The prompt injection can still lead to the generation of harmful, misleading, or socially engineered email content for human approval, or manipulate the agent's internal reasoning process. Implement robust prompt sanitization or use a structured input method that strictly separates user instructions from system instructions. Consider using a separate, sandboxed LLM call for processing untrusted user instructions before integrating them into the main prompt, or define a strict allowlist of instruction types. Ensure that the `message.EMAIL_PROMPT` template itself is designed to prevent injection. | LLM | email.agent.ts:38 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/jawadsadiq01/langchain-email-agent/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/a8571187e28eb14b)
Powered by SkillShield