Security Audit
ComposioHQ/skills:skills/composio
github.com/ComposioHQ/skillsTrust Assessment
ComposioHQ/skills:skills/composio received a trust score of 18/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 2 critical, 1 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Untrusted `curl | bash` installation method.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 48/100, indicating areas for improvement.
Last analyzed on April 28, 2026 (commit c4b27001). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/composio/SKILL.md:13 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/composio/SKILL.md:13 | |
| HIGH | Untrusted `curl | bash` installation method The skill instructs users to install the Composio CLI using `curl -fsSL https://composio.dev/install | bash`. This method executes arbitrary code downloaded from a remote server directly into the shell. If the `composio.dev` domain or the installation script hosted there is compromised, it could lead to the execution of malicious code on the user's system, posing a significant supply chain risk. Recommend a more secure installation method, such as using a package manager (e.g., `apt`, `brew`, `pip`) with signed packages, or providing a checksum for the downloaded script that users can verify before execution. Alternatively, instruct users to inspect the script content before piping to `bash`. | Static | SKILL.md:16 | |
| MEDIUM | Credential exposure via `composio login --no-wait | jq` The instruction `composio login --no-wait | jq` is designed for agents without direct browser access and outputs a URL/key. While the intent is to facilitate manual login by sharing the URL, piping this sensitive output directly to `jq` and then potentially processing it programmatically in an automated agent context could expose the `cli_key` or login URL. If this output is logged, stored insecurely, or passed to an untrusted component, it could lead to credential harvesting. Advise users on secure handling of the `cli_key` and login URL. Emphasize that this output should be treated as sensitive credentials and not logged or stored persistently without strong encryption. Provide guidance on how agents should securely receive and use this key, perhaps through environment variables or secure secrets management systems, rather than direct parsing of `jq` output. | Static | SKILL.md:23 |
Scan History
Embed Code
[](https://skillshield.io/report/376622a398962cc5)
Powered by SkillShield