Security Audit
affaan-m/everything-claude-code:.cursor/skills/configure-ecc
github.com/affaan-m/everything-claude-codeTrust Assessment
affaan-m/everything-claude-code:.cursor/skills/configure-ecc 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 24 findings: 11 critical, 12 high, 1 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Unpinned Git Clone Leads to Supply Chain Risk.
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 February 24, 2026 (commit db27ba1e). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings24
| 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 | .cursor/skills/configure-ecc/SKILL.md:17 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:43 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:183 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:188 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:189 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:190 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:198 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:208 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:285 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:293 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:294 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:17 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:43 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:183 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:188 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:189 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:190 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:198 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:208 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:285 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:293 | |
| 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 | .cursor/skills/configure-ecc/SKILL.md:294 | |
| HIGH | Unpinned Git Clone Leads to Supply Chain Risk The skill uses `git clone` to fetch the 'everything-claude-code' repository without specifying a fixed version (e.g., a commit hash or tag). This means the skill will always clone the latest version of the default branch. If the remote repository is compromised or a malicious change is introduced to its main branch, the skill will install potentially malicious code without explicit review, posing a significant supply chain risk. Pin the `git clone` operation to a specific commit hash or tag to ensure deterministic and auditable dependency fetching. For example: `git clone --depth 1 --branch <tag_or_branch> <repo_url> <destination_path>` or `git clone <repo_url> <destination_path> && cd <destination_path> && git checkout <commit_hash>`. | Static | SKILL.md:28 | |
| MEDIUM | Potential Prompt Injection via Processed Installed Files During the 'Optimize Installed Files' step, the skill instructs the host LLM to 'Read each installed SKILL.md' and 'Edit the SKILL.md files in-place'. Since the installed files originate from an unpinned `git clone` (as identified in SS-SC-001), their content is not guaranteed to be benign. If a malicious actor compromises the source repository, they could inject prompt injection instructions into the `SKILL.md` or rule files. When the LLM processes these files for 'optimization', it could be manipulated to perform unintended actions, effectively turning a supply chain compromise into a prompt injection attack against the host LLM. Mitigate the underlying supply chain risk by pinning the `git clone` to a specific version. Additionally, implement strict sanitization or validation of content from external sources before it is processed by the LLM, especially when the LLM is instructed to 'edit' or 'suggest' changes based on that content. Consider sandboxing the LLM's execution environment during such operations. | LLM | SKILL.md:170 |
Scan History
Embed Code
[](https://skillshield.io/report/1932b115507723e8)
Powered by SkillShield