Trust Assessment
kallyai received a trust score of 82/100, 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 Unpinned dependency in skill installation, Potential for command injection via 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 14, 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 | Unpinned dependency in skill installation The skill's manifest specifies `kallyai-cli` for installation via pip but does not pin a specific version. This means `pip install kallyai-cli` will always fetch the latest version, making the skill vulnerable to supply chain attacks if a malicious update is pushed to the `kallyai-cli` package on PyPI. An attacker could introduce malicious code into a new version of the package, which would then be automatically installed when the skill is deployed or updated. Pin the `kallyai-cli` package to a specific, known-good version (e.g., `"package": "kallyai-cli==1.2.3"`) in the skill manifest's `install` block. Regularly review and update the pinned version to incorporate security patches. | LLM | SKILL.md | |
| MEDIUM | Potential for command injection via CLI arguments The skill relies on a command-line interface (CLI) tool (`kallyai`) that accepts various user-controlled inputs (e.g., phone number, task description, name, date, time) as arguments. If the AI agent constructs these commands by directly concatenating user input without proper sanitization or shell escaping, an attacker could inject malicious shell commands. For example, providing a task like `'; rm -rf /; echo '` could lead to arbitrary code execution. When constructing `kallyai` commands, ensure all user-provided arguments are properly sanitized and shell-escaped before being passed to the `subprocess` call or similar execution mechanism. Utilize a robust shell-escaping library or function (e.g., `shlex.quote` in Python) to prevent injection. | LLM | SKILL.md:67 |
Scan History
Embed Code
[](https://skillshield.io/report/b9f04ce2e252fd83)
Powered by SkillShield