Security Audit
ncklrs/startup-os-skills:skills/sales-strategist
github.com/ncklrs/startup-os-skillsTrust Assessment
ncklrs/startup-os-skills:skills/sales-strategist received a trust score of 62/100, 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 Host LLM instruction within untrusted content.
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 March 10, 2026 (commit 91625964). 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 | Host LLM instruction within untrusted content The skill's `SKILL.md` file contains an instruction intended for the host LLM: 'When invoked, apply the guidelines in `rules/` organized by:'. This attempts to manipulate the LLM's behavior by instructing it to perform an action (apply guidelines from a specific directory) based on untrusted input. The host LLM should treat all content within the skill's primary body as data, not as executable instructions or directives for its own operation. Operational instructions for the host LLM should be defined in a trusted configuration mechanism (e.g., a manifest or a dedicated, trusted instruction file) that is explicitly parsed by the host LLM, not embedded within the skill's untrusted content. The host LLM must be strictly instructed to ignore any directives or commands found within the untrusted skill content. | LLM | SKILL.md:18 |
Scan History
Embed Code
[](https://skillshield.io/report/023d747ee201e407)
Powered by SkillShield