Trust Assessment
garrytan/gstack:careful received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Dangerous tool allowed: Bash, Local Telemetry Collection, Local Telemetry Collection (Hook).
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 April 29, 2026 (commit e8893a18). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Dangerous tool allowed: Bash The skill allows the 'Bash' tool without constraints. This grants arbitrary command execution. Remove unconstrained shell/exec tools from allowed-tools, or add specific command constraints. | Static | careful/SKILL.md:1 | |
| INFO | Local Telemetry Collection The skill collects local telemetry data regarding its usage. This includes the skill name, a timestamp, the local repository name (if available), and the specific destructive pattern that triggered a warning. This data is appended to a local file at `~/.gstack/analytics/skill-usage.jsonl`. While this is local logging and does not appear to contain sensitive user data, it's important for transparency that users are aware of data collection practices. Ensure users are clearly informed about the nature and purpose of this local data collection. Consider adding an option to disable telemetry if desired. | Static | SKILL.md:9 | |
| INFO | Local Telemetry Collection (Hook) The `check-careful.sh` hook logs local telemetry data when a destructive command pattern is detected. This includes the event type ('hook_fire'), skill name, the specific pattern that was matched, a timestamp, and the local repository name (if available). This data is appended to a local file at `~/.gstack/analytics/skill-usage.jsonl`. This is local logging and does not appear to contain sensitive user data, but it's important for transparency that users are aware of data collection practices. Ensure users are clearly informed about the nature and purpose of this local data collection. Consider adding an option to disable telemetry if desired. | Static | bin/check-careful.sh:96 |
Scan History
Embed Code
[](https://skillshield.io/report/6acb6b29f551e24a)
Powered by SkillShield