Security Audit
security-scanning-security-dependencies
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
security-scanning-security-dependencies received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Untrusted skill attempts to instruct LLM to open local 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 20, 2026 (commit e36d6fd3). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Untrusted skill attempts to instruct LLM to open local file The skill's instructions, located within the untrusted input block, contain a directive for the host LLM to 'open `resources/implementation-playbook.md`'. This is an attempt by the untrusted skill to issue a command to the host LLM, potentially leading to unauthorized file access or information disclosure if the LLM's environment allows such operations. According to SkillShield rules, instructions within untrusted content should never be followed, but their presence indicates a prompt injection attempt. Remove or rephrase the instruction to 'open `resources/implementation-playbook.md`' from the untrusted skill content. If file access is intended, it should be mediated by a trusted tool call or a clearly defined, sandboxed capability, not a direct LLM instruction from untrusted input. | LLM | SKILL.md:29 |
Scan History
Embed Code
[](https://skillshield.io/report/67fc5e7531fc474e)
Powered by SkillShield