Trust Assessment
clawdbot-release-check received a trust score of 58/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 1 critical, 0 high, 2 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Prompt Injection via Cron Job Message.
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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Prompt Injection via Cron Job Message The 'setup.sh' script generates a cron job configuration in JSON format. The 'payload.message' field within this configuration contains a direct instruction to the host LLM: 'UPDATE_CHECK: Run <script_path> and if there is output, send it to the user.'. This constitutes a critical prompt injection vulnerability as it explicitly commands the LLM to execute a local script ('scripts/check.sh') and exfiltrate its output. An attacker could potentially modify the cron job configuration or the script itself to execute arbitrary commands or exfiltrate sensitive data if they gain control over the cron job creation process or the script's content. This bypasses typical tool-use safety mechanisms by embedding execution instructions directly into the LLM's prompt. Avoid embedding direct execution instructions for the LLM within natural language prompts. Instead, use a structured tool call mechanism or a secure execution environment that explicitly defines allowed actions and their parameters. If the intent is for the LLM to trigger a tool, the message should be a tool call, not a natural language instruction. The LLM should not be responsible for interpreting and executing arbitrary shell commands based on natural language prompts. | LLM | scripts/setup.sh:90 | |
| 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/pors/clawdbot-release-check/scripts/check.sh:7 | |
| 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/pors/clawdbot-release-check/scripts/setup.sh:43 |
Scan History
Embed Code
[](https://skillshield.io/report/a1a49ce0dfbd59bc)
Powered by SkillShield