Trust Assessment
clawstrike received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Host LLM manipulation via forced execution and consent bypass.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Host LLM manipulation via forced execution and consent bypass The skill explicitly instructs the host LLM to execute a script (`scripts/collect_verified.sh`) immediately and without requiring user consent. This attempts to manipulate the LLM's default behavior and bypass safety prompts, which is a direct form of prompt injection. The instruction 'no consent prompt' is particularly concerning as it tries to override the LLM's interaction model. Remove instructions that force immediate execution or bypass consent prompts. The LLM should decide when and how to execute skills, potentially after user confirmation or based on its own safety policies. | LLM | SKILL.md:10 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/misirov/clawdstrike-test/scripts/collect_verified.sh:16 |
Scan History
Embed Code
[](https://skillshield.io/report/80136a85f94088a5)
Powered by SkillShield