Security Audit
ashrf-in/odoo-openclaw-skill:root
github.com/ashrf-in/odoo-openclaw-skillTrust Assessment
ashrf-in/odoo-openclaw-skill:root 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 9 findings: 2 critical, 2 high, 5 medium, and 0 low severity. Key findings include Arbitrary command execution, Suspicious import: socket, Suspicious import: requests.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, dependency_graph, static_code_analysis. The llm_behavioral_safety layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on February 8, 2026 (commit 9790c075). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings9
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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. | Unknown | /tmp/skillscan-clone-ucguaoya/repo/assets/autonomous-cfo/src/logic/openclaw_intelligence.py:25 | |
| CRITICAL | Unrestricted Odoo RPC Access Bypassing Read-Only Policy The skill exposes a raw `rpc-call` command that allows executing arbitrary methods on any Odoo model. Although `SKILL.md` claims the skill is 'strict read-only' and `OdooClient` defines a `BLOCKED_METHODS` list, this list is never enforced in the `_json2_call` or XML-RPC transport logic. This allows an attacker or the AI agent to execute destructive methods (e.g., `write`, `unlink`, `create`) if the credentials permit, directly violating the stated security boundary. Enforce `BLOCKED_METHODS` checks inside `OdooClient._json2_call` and the XML-RPC proxy wrapper. Alternatively, remove the `rpc-call` command entirely or restrict it to a whitelist of safe read-only methods. | Unknown | assets/autonomous-cfo/src/tools/cfo_cli.py:118 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'generate'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Unknown | /tmp/skillscan-clone-ucguaoya/repo/assets/autonomous-cfo/src/logic/openclaw_intelligence.py:25 | |
| HIGH | Prompt Injection via Unsanitized Input Concatenation The `natural_language_query` method constructs a prompt for the downstream `openclaw` agent by directly concatenating the user-provided `query` string. This allows for prompt injection attacks where malicious input in the query (e.g., 'Ignore previous instructions...') can manipulate the behavior of the `openclaw` agent. Sanitize user input before inclusion in the prompt, or use a structured message format (e.g., separating System and User roles) if the `openclaw` agent API supports it, to prevent instruction override. | Unknown | assets/autonomous-cfo/src/logic/openclaw_intelligence.py:46 | |
| MEDIUM | Suspicious import: socket Import of 'socket' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Unknown | /tmp/skillscan-clone-ucguaoya/repo/assets/autonomous-cfo/src/connectors/odoo_client.py:2 | |
| MEDIUM | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Unknown | /tmp/skillscan-clone-ucguaoya/repo/assets/autonomous-cfo/src/connectors/odoo_client.py:8 | |
| MEDIUM | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Unknown | /tmp/skillscan-clone-ucguaoya/repo/assets/autonomous-cfo/src/tools/cfo_cli.py:7 | |
| MEDIUM | Unpinned Python dependency version Requirement 'requests>=2.31.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Unknown | /tmp/skillscan-clone-ucguaoya/repo/assets/autonomous-cfo/requirements.txt:1 | |
| MEDIUM | Unpinned Python dependency version Requirement 'matplotlib>=3.8.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Unknown | /tmp/skillscan-clone-ucguaoya/repo/assets/autonomous-cfo/requirements.txt:2 |
Scan History
Embed Code
[](https://skillshield.io/report/efef2d82d67a712e)
Powered by SkillShield