Trust Assessment
jetpack-compose received a trust score of 78/100, 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 Missing required field: name, Excessive tool permissions declared.
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 15, 2026 (commit 1823c3f6). 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 | Excessive tool permissions declared The skill declares broad and potentially dangerous permissions (`Bash`, `Write`, `Edit`, `Read`, `Glob`, `Grep`) that are not justified by its stated purpose as a 'Jetpack Compose and Kotlin expert'. The `Bash` permission allows arbitrary command execution, `Write` and `Edit` allow modification of any file, and `Read`, `Glob`, `Grep` allow extensive file system access and data exfiltration. These permissions could be misused by the LLM if prompted, leading to system compromise, data loss, or sensitive information leakage. Restrict `allowed-tools` to only those strictly necessary for the skill's function. For a 'Jetpack Compose expert', `Read` and potentially `Write`/`Edit` for code generation might be acceptable, but `Bash`, `Glob`, and `Grep` are generally excessive and should be removed unless a specific, well-justified use case exists. | Static | SKILL.md:1 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | plugins/specweave-mobile/skills/jetpack-compose/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/22547ff24a51063d)
Powered by SkillShield