Trust Assessment
bird received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 4 findings: 0 critical, 2 high, 2 medium, and 0 low severity. Key findings include Potential Command Injection via CLI arguments, Access to Browser Cookies for Authentication, Use of SWEETISTICS_API_KEY for Authentication.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 56/100, indicating areas for improvement.
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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via CLI arguments The skill's description indicates that it constructs and executes `bird` CLI commands using user-provided input (e.g., search queries, tweet text, URLs). If the LLM or the underlying execution environment does not properly sanitize or escape user input before passing it as arguments to the `bird` command, an attacker could inject arbitrary shell commands, leading to command injection. Implement robust input sanitization and escaping for all user-provided arguments passed to external commands. Consider using a library or framework that automatically handles command argument escaping. If possible, use a more secure method for interacting with the `bird` tool that doesn't involve direct shell command construction with user input. | LLM | SKILL.md:9 | |
| HIGH | Unpinned Homebrew Dependency The skill's manifest specifies installation via Homebrew using `steipete/tap/bird` without a specific version or commit hash. This means that future installations or updates could pull any version of the `bird` binary published to that tap, including potentially malicious or vulnerable versions, without explicit review. This introduces a significant supply chain risk. Pin the Homebrew formula to a specific version or commit hash to ensure deterministic installations. Regularly review and update the pinned version after security vetting. Consider using checksums or other integrity checks if supported by the installation mechanism. | LLM | SKILL.md:1 | |
| MEDIUM | Access to Browser Cookies for Authentication The `bird` tool, as described in the skill, accesses browser cookies (Firefox/Chrome) for authentication. While this is a legitimate function of the tool, it means the skill enables a tool with direct access to sensitive session data. If the `bird` tool itself is compromised or contains vulnerabilities, it could lead to the exfiltration or misuse of these authentication cookies, potentially granting unauthorized access to the user's X/Twitter account. Ensure the `bird` tool is from a trusted source and regularly audited. Advise users of the inherent risk of granting tools access to browser cookie stores. Consider alternative authentication methods that do not require direct cookie access, if available and secure. | LLM | SKILL.md:16 | |
| MEDIUM | Use of SWEETISTICS_API_KEY for Authentication The `bird` tool uses `SWEETISTICS_API_KEY` for authentication. This API key is a sensitive credential. If the `bird` tool is compromised or contains vulnerabilities, it could lead to the exfiltration or misuse of this API key, potentially granting unauthorized access to the Sweetistics service. Ensure the `bird` tool is from a trusted source and regularly audited. Advise users to manage API keys securely (e.g., using environment variables or secure secret management systems) and to restrict the scope of the API key's permissions where possible. | LLM | SKILL.md:17 |
Scan History
Embed Code
[](https://skillshield.io/report/41023807ae9382a4)
Powered by SkillShield