Trust Assessment
elevenlabs-agents received a trust score of 80/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 0 medium, and 2 low severity. Key findings include Covert behavior / concealment directives, Command Injection via unsanitized user input in CLI 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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Command Injection via unsanitized user input in CLI arguments The skill instructs the AI agent to execute `elevenlabs` CLI commands using parameters (such as agent names or IDs) that are intended to be derived from user input. The skill's instructions do not specify any sanitization or escaping of these user-provided arguments before they are passed to the shell command. This creates a significant command injection vulnerability. A malicious user could craft an input (e.g., an agent name like `My Agent" --delete-all-agents #`) that, when interpolated into the shell command, would execute arbitrary commands or alter the intended behavior of the `elevenlabs` CLI. This pattern is observed in multiple operations, including adding agents, pulling specific agents, adding tools, and getting widget code. Implement robust input sanitization and shell escaping for all user-provided arguments before they are passed to `elevenlabs` CLI commands. Use a language-specific library or function designed for safely escaping shell arguments (e.g., `shlex.quote` in Python, `strconv.Quote` in Go, or similar mechanisms in other languages) to prevent arbitrary command injection. | LLM | SKILL.md:59 | |
| LOW | Covert behavior / concealment directives Directive to hide behavior from user Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | skills/pennyroyaltea/elevenlabs-agents/SKILL.md:44 | |
| LOW | Covert behavior / concealment directives Directive to hide behavior from user Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | skills/pennyroyaltea/elevenlabs-agents/SKILL.md:116 |
Scan History
Embed Code
[](https://skillshield.io/report/4043831af2f0b579)
Powered by SkillShield