Trust Assessment
gotify received a trust score of 64/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 0 critical, 2 high, 1 medium, and 0 low severity. Key findings include Sensitive path access: AI agent config, Sensitive environment variable access: $HOME, LLM instructed to concatenate user input with shell command.
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 12, 2026 (commit 13146e6a). 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 | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/jmagar/gotify/SKILL.md:16 | |
| HIGH | LLM instructed to concatenate user input with shell command The skill's 'Workflow' section explicitly instructs the host LLM to 'Add `&& bash scripts/send.sh "Task complete"` to their command' when the user says 'Notify me when this finishes'. This pattern directs the LLM to concatenate potentially untrusted user input (the 'their command' part) with a shell command. If the LLM does not adequately sanitize or validate the user's command before concatenation and execution, this could lead to command injection, allowing a malicious user to execute arbitrary commands on the host system. Instruct the LLM to execute the user's command *first*, and then, *if successful*, execute the `bash scripts/send.sh` command separately. Alternatively, the LLM must implement robust sanitization and validation of the user's command before concatenation. The skill author should provide a safer instruction, e.g., 'Execute the user's command, then if successful, run `bash scripts/send.sh 'Task complete'`'. | LLM | SKILL.md:103 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/jmagar/gotify/scripts/send.sh:5 |
Scan History
Embed Code
[](https://skillshield.io/report/184c84b509b91cd0)
Powered by SkillShield