Trust Assessment
kimi-delegation-skill received a trust score of 86/100, 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 Skill requests excessive `Python(Read Write)` permissions.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill requests excessive `Python(Read Write)` permissions The skill's manifest declares `Python(Read Write)` permissions. The `SKILL.md` describes the skill's function as delegating user prompts verbatim to a KIMI model and returning its response. This functionality does not inherently require broad read and write access to the filesystem. Granting such broad permissions significantly increases the attack surface, allowing potential data exfiltration, command injection, or unauthorized file modification if the underlying Python code (not provided) is compromised or malicious. The skill description does not justify the need for such broad access. Restrict `allowed-tools` to the minimum necessary permissions. If file operations are required, specify exact file paths or more granular permissions (e.g., `Python(Read /path/to/model_config.json)`). If no file I/O is needed, remove `Read Write` entirely. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/53e32890a58965ff)
Powered by SkillShield