Trust Assessment
subagent-driven-development 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 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Path Traversal and Arbitrary File Write in task-brief script.
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 August 1, 2026 (commit 44c9b2d6). 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 | Path Traversal and Arbitrary File Write in task-brief script The `scripts/task-brief` script accepts a `TASK_NUMBER` (`n`) parameter without validation. This parameter is directly used to construct the output file path (`out="$dir/task-${n}-brief.md"`). An attacker can supply a path traversal string (e.g., `../../../../path/to/file`) as the task number, causing the script to write the extracted task content to an arbitrary location on the filesystem, potentially overwriting critical files or configuration. Validate that the `TASK_NUMBER` parameter contains only integers or safe alphanumeric characters before using it to construct file paths. For example, add a check: `if [[ ! "$n" =~ ^[0-9]+$ ]]; then echo "Invalid task number" >&2; exit 1; fi`. | LLM | scripts/task-brief:23 |
Scan History
Embed Code
[](https://skillshield.io/report/f84f9566bbd7b85a)
Powered by SkillShield