Security Audit
loki-mode
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
This report is partially verified. Deterministic layers ran, but LLM behavioral analysis (L4) was not executed for this scan.
The current score of 10/100 is provisional and may change after a full L4 verification run.
Last analyzed on February 20, 2026 (commit 9f5351e8). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings13
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | skills/loki-mode/autonomy/run.sh:1195 | |
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | skills/loki-mode/autonomy/run.sh:1199 | |
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | skills/loki-mode/demo/record-full-demo.sh:114 | |
| CRITICAL | Arbitrary command execution Python dynamic code execution (exec/eval/compile) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/loki-mode/benchmarks/results/2026-01-05-00-49-17/humaneval-solutions/160.py:29 | |
| CRITICAL | Arbitrary command execution Python dynamic code execution (exec/eval/compile) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/loki-mode/benchmarks/results/humaneval-loki-solutions/160.py:34 | |
| 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 | skills/loki-mode/SKILL.md:116 | |
| CRITICAL | Dangerous call: eval() Call to 'eval()' detected in function 'do_algebra'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/loki-mode/benchmarks/results/2026-01-05-00-49-17/humaneval-solutions/160.py:29 | |
| CRITICAL | Dangerous call: eval() Call to 'eval()' detected in function 'do_algebra'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/loki-mode/benchmarks/results/humaneval-loki-solutions/160.py:34 | |
| 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 | skills/loki-mode/SKILL.md:116 | |
| 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/loki-mode/autonomy/run.sh:243 | |
| 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/loki-mode/scripts/export-to-vibe-kanban.sh:8 | |
| MEDIUM | Unpinned npm dependency version Dependency 'better-sqlite3' is not pinned to an exact version ('^9.0.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/loki-mode/examples/todo-app-generated/backend/package.json | |
| MEDIUM | Unpinned npm dependency version Dependency 'react' is not pinned to an exact version ('^19.2.3'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/loki-mode/examples/todo-app-generated/frontend/package.json |