Security Audit
verification-agent
github.com/skillcreatorai/Ai-Agent-SkillsTrust Assessment
verification-agent received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 8 findings: 7 critical, 0 high, 1 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Insecure Temporary Directory Usage (Predictable Path in Shared /tmp).
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on October 1, 2026 (commit 6d95c788). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings8
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/verification-agent/scripts/content-index.mjs:57 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/verification-agent/scripts/content-index.mjs:73 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/verification-agent/scripts/lib/corpus.mjs:34 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/verification-agent/scripts/lib/match.mjs:72 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/verification-agent/scripts/lib/match.mjs:73 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/verification-agent/scripts/verify.mjs:72 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/verification-agent/scripts/verify.mjs:125 | |
| MEDIUM | Insecure Temporary Directory Usage (Predictable Path in Shared /tmp) The script uses a predictable, shared temporary directory path ('/tmp/verification-agent-cache') to cache corpus files. On multi-user systems, an attacker can pre-create this directory or place symlinks inside it pointing to sensitive files. When the script writes to the cache file using 'fs.writeFileSync', it will follow the symlink and overwrite the target file, potentially leading to local privilege escalation or denial of service. Use a secure temporary directory creation method, such as 'fs.mkdtempSync' inside the OS temp directory, or append the current user's UID/username to the directory name to prevent other users from pre-creating or writing to it. | LLM | scripts/lib/corpus.mjs:18 |
Scan History
Embed Code
[](https://skillshield.io/report/55b3adf35ce7d7ab)
Powered by SkillShield