Trust Assessment
quests received a trust score of 79/100, 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, Arbitrary File Write via `export --file`.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Arbitrary File Write via `export --file` The `quest export` command, as described in the `SKILL.md` documentation, allows specifying an arbitrary file path using the `--file` argument. If the underlying Python script (`scripts/quest.py`) directly uses this user-provided path without proper sanitization or restriction to a designated output directory (e.g., within `$WORKSPACE/data`), an attacker could leverage this to write quest data to any location on the filesystem where the agent has write permissions. This could lead to overwriting critical system files, user configuration files (e.g., `~/.bashrc`, `~/.ssh/authorized_keys`), or exfiltrating data by writing it to a publicly accessible web directory. Implement strict path validation for the `--file` argument in the `export` command within `scripts/quest.py`. Paths should be canonicalized and restricted to a safe, designated directory (e.g., `$WORKSPACE/data` or a user-specified output directory within `WORKSPACE`). Prevent directory traversal sequences like `../` and ensure that the resolved path does not escape the intended base directory. | LLM | SKILL.md:105 | |
| 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/poloio/quests/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/cc9794ab2b220fdc)
Powered by SkillShield