Security Audit
lastpass-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
lastpass-automation 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 Broad access to Lastpass operations via generic execution tools.
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 27904475). 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 | Broad access to Lastpass operations via generic execution tools The skill provides access to Lastpass automation through Rube MCP, exposing generic execution tools like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. These tools allow an AI agent to perform a wide range of Lastpass operations by specifying `tool_slug` and `arguments`. While the skill's purpose is automation, granting such broad, unconstrained access to a credential manager via generic execution primitives significantly increases the attack surface. If the AI agent's decision-making process is compromised (e.g., via prompt injection), a malicious actor could potentially trick the agent into executing arbitrary Lastpass operations, such as retrieving sensitive credentials, modifying account settings, or performing other unauthorized actions. The skill documentation itself highlights the power of these tools without describing any inherent guardrails or scope limitations within the skill's definition. Implement fine-grained access control for Lastpass operations, limiting the scope of actions an agent can perform. Instead of generic `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH` for all Lastpass tasks, consider creating specific, narrowly scoped tools for common, safe operations. Ensure robust input validation and sanitization for `tool_slug` and `arguments` if they are derived from untrusted user input. Consider requiring explicit user confirmation for sensitive Lastpass operations. | LLM | SKILL.md:49 |
Scan History
Embed Code
[](https://skillshield.io/report/320c38e534224531)
Powered by SkillShield