Security Audit
changelog-generator
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
changelog-generator received a trust score of 79/100, 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, 2 high, 0 medium, and 0 low severity. Key findings include Skill description implies arbitrary file read, risking data exfiltration, Skill description implies arbitrary file write, risking system compromise.
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 27904475). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill description implies arbitrary file read, risking data exfiltration The skill's description indicates it can read user-specified files (e.g., 'CHANGELOG_STYLE.md'). If the underlying implementation allows arbitrary file paths without proper validation or sandboxing, a malicious user could instruct the skill to read sensitive files (e.g., `/etc/passwd`, `~/.ssh/id_rsa`), leading to data exfiltration. This represents an excessive permission if not properly constrained. The skill's implementation must strictly validate and sandbox file paths provided by the user for reading. Limit read access to specific, intended directories or file types, and prevent access to sensitive system files. | LLM | SKILL.md:59 | |
| HIGH | Skill description implies arbitrary file write, risking system compromise The skill's description indicates it can write to user-specified files (e.g., 'Save output directly to CHANGELOG.md'). If the underlying implementation allows arbitrary file paths without proper validation or sandboxing, a malicious user could instruct the skill to write to critical system locations, overwrite important files, or inject malicious scripts. This represents an excessive permission that could lead to system compromise or command injection if the written file is later executed. The skill's implementation must strictly validate and sandbox file paths provided by the user for writing. Limit write access to specific, intended directories or file types, and prevent overwriting of critical system files or writing to executable paths. | LLM | SKILL.md:82 |
Scan History
Embed Code
[](https://skillshield.io/report/fcab1abea018c171)
Powered by SkillShield