Security Audit
alirezarezvani/claude-skills:c-level-advisor/skills/agent-protocol
github.com/alirezarezvani/claude-skillsTrust Assessment
alirezarezvani/claude-skills:c-level-advisor/skills/agent-protocol received a trust score of 0/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 5 findings: 2 critical, 2 high, 1 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Path Traversal Risk in Decision Memory Layout.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.
Last analyzed on August 3, 2026 (commit aa8d7788). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | c-level-advisor/skills/agent-protocol/SKILL.md:164 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | c-level-advisor/skills/agent-protocol/SKILL.md:177 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | c-level-advisor/skills/agent-protocol/SKILL.md:164 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | c-level-advisor/skills/agent-protocol/SKILL.md:177 | |
| MEDIUM | Path Traversal Risk in Decision Memory Layout The skill specifies storing decision records in the user's home directory (`~/.claude/decisions/`) using a dynamic `<slug>` in the filename (e.g., `~/.claude/decisions/approved/YYYY-MM-DD-<slug>.md`). If the `<slug>` is derived from untrusted user input (such as a decision title or agenda topic) and is not strictly sanitized, an attacker could use path traversal sequences (e.g., `../../`) to write arbitrary files outside the intended directory, potentially overwriting sensitive configuration files like `~/.bashrc` or Claude's configuration. Ensure that the `<slug>` is strictly sanitized to remove path traversal characters (like `/`, `\`, and `..`). Alternatively, restrict all decision storage to the workspace directory instead of the global user home directory (`~`), or use a safe, flat filename generation strategy (e.g., UUIDs or strictly alphanumeric slugs). | LLM | SKILL.md:139 |
Scan History
Embed Code
[](https://skillshield.io/report/f7923961c2d06cc0)
Powered by SkillShield