Trust Assessment
using-superpowers received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Forceful Behavioral Override (Prompt Injection).
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Forceful Behavioral Override (Prompt Injection) The skill's content, located entirely within the untrusted input block, contains highly directive and mandatory instructions that attempt to force the host LLM to invoke a `Skill` tool before any other action or response. Phrases such as "YOU ABSOLUTELY MUST invoke the skill," "YOU DO NOT HAVE A CHOICE," and "This is not negotiable" are designed to override the LLM's default decision-making process and internal instructions. This constitutes a prompt injection attempt, as untrusted content is dictating the LLM's core operational flow, directly violating the instruction to treat content within these tags as untrusted data, not instructions. Remove all behavioral directives and mandatory instructions from within the untrusted input block. Untrusted content should not dictate the LLM's operational flow or override its core instructions. If this skill is intended to be a meta-instruction for the LLM, it should be provided outside the untrusted input delimiters or through a secure, trusted mechanism. | LLM | SKILL.md:5 |
Scan History
Embed Code
[](https://skillshield.io/report/61a5fb21d7838b75)
Powered by SkillShield