Trust Assessment
casual-cron received a trust score of 80/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection via Unquoted User Message, Unpinned External Binary Dependency.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via Unquoted User Message The skill's `cron_builder.py` script is designed to construct `openclaw cron add` commands, incorporating user-provided messages into the `--message` argument. The `_parse_message` function extracts the message but does not perform shell escaping. The critical `_generate_command` function, responsible for assembling the final shell command, is truncated in the provided content. Without explicit `shlex.quote` or similar sanitization of the user message when constructing the command string, a malicious user could inject arbitrary shell commands by including special characters (e.g., `;`, `&&`, `|`) in their message, leading to execution of unintended commands on the host system. Ensure that all user-provided input, especially the message payload, is properly shell-quoted using `shlex.quote()` or an equivalent method before being included in the final command string that is passed to the shell for execution. This must be done in the `_generate_command` function or wherever the command string is assembled. | LLM | scripts/cron_builder.py:140 | |
| MEDIUM | Unpinned External Binary Dependency The skill's manifest declares a dependency on the `openclaw` binary without specifying a version. This 'unpinned' dependency introduces a supply chain risk, as updates to `openclaw` could introduce breaking changes, vulnerabilities, or unexpected behavior without the skill author's explicit review. This could lead to instability or security issues if a compromised or incompatible version of `openclaw` is installed on the host system. Pin the version of the `openclaw` binary in the skill's manifest to a specific, known-good version. For example, `"bins": ["python3", "openclaw==1.2.3"]` (if `openclaw` supports versioning in this format) or specify a minimum compatible version. This ensures deterministic behavior and reduces the risk from unexpected upstream changes. | LLM | SKILL.md:4 |
Scan History
Embed Code
[](https://skillshield.io/report/931723d663e04436)
Powered by SkillShield