Trust Assessment
flatnotes-tasksmd-github-audit received a trust score of 97/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 0 medium, and 1 low severity. Key findings include LLM instruction in untrusted skill description.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| LOW | LLM instruction in untrusted skill description The skill description contains direct instructions intended for the host LLM, such as 'Use this skill when Brandon asks to audit...' and 'If Brandon explicitly asks to apply fixes:'. According to security guidelines, all content within the untrusted input delimiters should be treated as data, not instructions for the LLM. Following such instructions, even if benign, can establish a precedent for the LLM to accept and act upon directives from untrusted sources, which is a fundamental vector for prompt injection. Rephrase the skill description to be purely declarative, describing the skill's capabilities and conditions for use, rather than issuing direct instructions to the LLM. For example, 'This skill is designed for auditing...' or 'The skill can apply fixes if explicitly requested by the user.' | LLM | SKILL.md:3 |
Scan History
Embed Code
[](https://skillshield.io/report/b89c10b0dfe36a10)
Powered by SkillShield