Trust Assessment
collaboration-helper received a trust score of 41/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Arbitrary File Read/Write via --data argument.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| 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. | Manifest | skills/crimsondevil333333/collaboration-helper/tests/test_collaboration_helper.py:12 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_cli'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/crimsondevil333333/collaboration-helper/tests/test_collaboration_helper.py:12 | |
| HIGH | Arbitrary File Read/Write via --data argument The `scripts/collaboration_helper.py` script allows users to specify an arbitrary file path for the `tasks.json` state file using the `--data` command-line argument. This enables an attacker to read the content of any file accessible to the agent (if it's valid JSON) or, more critically, overwrite any file with JSON data by using the `add` or `complete` commands. This could lead to data destruction, corruption, or potentially privilege escalation if critical system files are targeted. The `SKILL.md` explicitly mentions `--workspace /path/to/workspace` which confirms the intent to allow path manipulation, but without proper validation, this becomes a severe vulnerability. Restrict the `--data` argument to a specific, sandboxed directory (e.g., `Path.cwd() / 'data'`) or validate the path to ensure it does not escape the intended data directory. Implement strict path sanitization to prevent directory traversal attacks (e.g., `../`). Alternatively, use a more secure storage mechanism that doesn't rely on arbitrary file paths. | LLM | scripts/collaboration_helper.py:109 |
Scan History
Embed Code
[](https://skillshield.io/report/f27f4e84ae56e2c1)
Powered by SkillShield