Trust Assessment
dilbert received a trust score of 49/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 1 critical, 1 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Missing required field: name, Credential Exposure: Hardcoded API Token Placeholder.
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 13, 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 | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Node.js child_process require Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/hjanuschka/dilbert/dilbert.js:7 | |
| HIGH | Credential Exposure: Hardcoded API Token Placeholder The `daily_dilbert.sh` script contains a placeholder for a Telegram bot token (`<YOUR_BOT_TOKEN>`). If a real token is hardcoded directly into this script and committed to source control, it poses a significant credential exposure risk. Secrets should be managed securely, e.g., via environment variables or a dedicated secret management system, not hardcoded directly into scripts. Replace `<YOUR_BOT_TOKEN>` with a secure method for retrieving the token, such as an environment variable (e.g., `$TELEGRAM_BOT_TOKEN`). Ensure that the token is never hardcoded directly into the script or committed to version control. | LLM | daily_dilbert.sh:14 | |
| 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/hjanuschka/dilbert/SKILL.md:1 | |
| INFO | Reliance on External Content Sources The `skill.sh` script fetches comic images from external domains (assets.amuniversal.com, imgs.xkcd.com). While the script attempts to verify the file type using the `file` command, reliance on external content introduces a supply chain risk. If these external sources were compromised or served malicious content (e.g., specially crafted images exploiting viewer vulnerabilities), the skill could inadvertently deliver harmful payloads. The risk is mitigated by file type checks, but not entirely eliminated. Consider implementing additional content validation, such as hashing known good images or using a trusted proxy/cache. Ensure the image viewer used by the agent is robust against malicious image formats. Regularly review the integrity of external sources if possible. | LLM | skill.sh:20 |
Scan History
Embed Code
[](https://skillshield.io/report/66dd57c1f901dbf5)
Powered by SkillShield