Trust Assessment
sol-build-session received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 4 findings: 0 critical, 1 high, 3 medium, and 0 low severity. Key findings include Missing required field: name, Sensitive environment variable access: $HOME, Command Injection via Unsanitized Argument.
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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Command Injection via Unsanitized Argument The `pick-task.sh` script uses the first command-line argument (`$1`) directly as a file path (`IDEAS_FILE`) without proper sanitization or quoting. This variable is then used in a `grep` command. An attacker could provide a malicious string as `$1` (e.g., `'; rm -rf /; #'`) to inject and execute arbitrary shell commands, leading to system compromise or data loss. Additionally, an attacker could specify a path to a sensitive file (e.g., `/etc/passwd`) to read its contents, leading to data exfiltration. Sanitize or validate the `IDEAS_FILE` variable to ensure it is a safe and expected file path. If the script must accept arbitrary file paths, use a safer method to read the file content that does not involve direct shell expansion of the filename in command arguments. For example, use `read -r` in a loop or ensure the argument is properly quoted for the specific command, though direct argument injection is hard to prevent without validation. A robust solution would be to strictly validate the input against a whitelist of allowed characters or patterns for file paths, or to ensure the script is only ever called with trusted, internally generated arguments. | LLM | pick-task.sh:15 | |
| 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 | skills/stevenartzt/sol-build-session/SKILL.md:1 | |
| 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/stevenartzt/sol-build-session/pick-task.sh:5 | |
| 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/stevenartzt/sol-build-session/session-log.sh:5 |
Scan History
Embed Code
[](https://skillshield.io/report/cb779506f9430e2f)
Powered by SkillShield