Trust Assessment
email-mentions received a trust score of 87/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Unpinned dependency on local skill for critical security function.
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 | |
|---|---|---|---|---|
| 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/gigi-trifle/email-mentions/email-mentions.sh:7 | |
| MEDIUM | Unpinned dependency on local skill for critical security function The skill relies on another local skill, 'indirect-prompt-injection', for its core prompt injection scanning functionality. The path to this dependency is hardcoded, but there is no mechanism to pin its version or ensure its integrity. If the 'indirect-prompt-injection' skill is compromised or updated with malicious code, this skill's security defenses would be bypassed, potentially leading to prompt injection attacks against the agent. Implement a mechanism to pin the version or commit hash of the 'indirect-prompt-injection' skill. This could involve checking a hash of the `sanitize.py` script before execution, or using a skill management system that enforces versioning for local skill dependencies. | LLM | email-mentions.sh:15 |
Scan History
Embed Code
[](https://skillshield.io/report/219c2ed38261d5f0)
Powered by SkillShield