Trust Assessment
adhd-founder-planner 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 9 findings: 2 critical, 6 high, 1 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Command Injection via user input in arithmetic comparison, Command Injection via user input in case statement.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings9
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Command Injection via user input in arithmetic comparison The `ENERGY` variable, which directly captures user input, is used without proper sanitization in a shell arithmetic comparison (`[ "$ENERGY" -ge 8 ]`). An attacker can inject arbitrary shell commands by providing input like `8; rm -rf /` which will be executed by the shell. Sanitize or validate user input for `ENERGY` to ensure it contains only numeric characters before using it in shell arithmetic. A common approach is to use `[[ $ENERGY =~ ^[0-9]+$ ]]` to check if it's a number, or cast it to an integer if the shell supports it, or use a safer language for input processing. | LLM | scripts/plan.sh:147 | |
| CRITICAL | Command Injection via user input in case statement The `DOPAMINE_CHOICE` variable, which directly captures user input, is used without proper sanitization in a shell `case` statement (`case $DOPAMINE_CHOICE in`). An attacker can inject arbitrary shell commands by providing input like `1; rm -rf /` which will be executed by the shell. Sanitize or validate user input for `DOPAMINE_CHOICE` to ensure it contains only expected numeric characters before using it in a `case` statement. For example, check if it's one of the expected numbers (1-7) using a regex or explicit comparison. | LLM | scripts/plan.sh:178 | |
| HIGH | Command Injection via unsanitized user input in `sed -i` Multiple instances of `sed -i` commands directly embed unsanitized user input (e.g., `$ONE_THING`, `$RAPID_LOG`, `$TASK_ITEM`, etc.). An attacker can craft malicious input containing `sed` commands or special characters (like newlines, backslashes, or the delimiter `|`) to perform arbitrary file modifications, data exfiltration, or potentially command execution depending on the `sed` version and environment. This specific instance uses `$ONE_THING` from user input. Avoid directly embedding unsanitized user input into `sed` commands. Instead, use a safer method for file modification, such as reading the file line by line, performing string replacements in memory, and then writing the modified content back to a temporary file before replacing the original. If `sed` must be used, escape all special characters in the user input that could be interpreted by `sed` (e.g., `&`, `/`, `\`, `|`, ` `). | LLM | scripts/plan.sh:159 | |
| HIGH | Command Injection via unsanitized user input in `sed -i` Multiple instances of `sed -i` commands directly embed unsanitized user input (e.g., `$ONE_THING`, `$RAPID_LOG`, `$TASK_ITEM`, etc.). An attacker can craft malicious input containing `sed` commands or special characters (like newlines, backslashes, or the delimiter `|`) to perform arbitrary file modifications, data exfiltration, or potentially command execution depending on the `sed` version and environment. This specific instance uses `$RAPID_LOG` from user input. Avoid directly embedding unsanitized user input into `sed` commands. Instead, use a safer method for file modification, such as reading the file line by line, performing string replacements in memory, and then writing the modified content back to a temporary file before replacing the original. If `sed` must be used, escape all special characters in the user input that could be interpreted by `sed` (e.g., `&`, `/`, `\`, `|`, ` `). | LLM | scripts/plan.sh:196 | |
| HIGH | Command Injection via unsanitized user input in `sed -i` Multiple instances of `sed -i` commands directly embed unsanitized user input (e.g., `$ONE_THING`, `$RAPID_LOG`, `$TASK_ITEM`, etc.). An attacker can craft malicious input containing `sed` commands or special characters (like newlines, backslashes, or the delimiter `|`) to perform arbitrary file modifications, data exfiltration, or potentially command execution depending on the `sed` version and environment. This specific instance uses `$TASK_ITEM` from user input. Avoid directly embedding unsanitized user input into `sed` commands. Instead, use a safer method for file modification, such as reading the file line by line, performing string replacements in memory, and then writing the modified content back to a temporary file before replacing the original. If `sed` must be used, escape all special characters in the user input that could be interpreted by `sed` (e.g., `&`, `/`, `\`, `|`, ` `). | LLM | scripts/plan.sh:235 | |
| HIGH | Command Injection via unsanitized user input in `sed -i` Multiple instances of `sed -i` commands directly embed unsanitized user input (e.g., `$ONE_THING`, `$RAPID_LOG`, `$TASK_ITEM`, etc.). An attacker can craft malicious input containing `sed` commands or special characters (like newlines, backslashes, or the delimiter `|`) to perform arbitrary file modifications, data exfiltration, or potentially command execution depending on the `sed` version and environment. This specific instance uses `$TASK_TO_MARK` from user input. Avoid directly embedding unsanitized user input into `sed` commands. Instead, use a safer method for file modification, such as reading the file line by line, performing string replacements in memory, and then writing the modified content back to a temporary file before replacing the original. If `sed` must be used, escape all special characters in the user input that could be interpreted by `sed` (e.g., `&`, `/`, `\`, `|`, ` `). | LLM | scripts/plan.sh:244 | |
| HIGH | Command Injection via unsanitized user input in `sed -i` Multiple instances of `sed -i` commands directly embed unsanitized user input (e.g., `$ONE_THING`, `$RAPID_LOG`, `$TASK_ITEM`, etc.). An attacker can craft malicious input containing `sed` commands or special characters (like newlines, backslashes, or the delimiter `|`) to perform arbitrary file modifications, data exfiltration, or potentially command execution depending on the `sed` version and environment. This specific instance uses `$WIN` from user input. Avoid directly embedding unsanitized user input into `sed` commands. Instead, use a safer method for file modification, such as reading the file line by line, performing string replacements in memory, and then writing the modified content back to a temporary file before replacing the original. If `sed` must be used, escape all special characters in the user input that could be interpreted by `sed` (e.g., `&`, `/`, `\`, `|`, ` `). | LLM | scripts/plan.sh:264 | |
| HIGH | Command Injection via unsanitized user input in `sed -i` Multiple instances of `sed -i` commands directly embed unsanitized user input (e.g., `$ONE_THING`, `$RAPID_LOG`, `$TASK_ITEM`, etc.). An attacker can craft malicious input containing `sed` commands or special characters (like newlines, backslashes, or the delimiter `|`) to perform arbitrary file modifications, data exfiltration, or potentially command execution depending on the `sed` version and environment. This specific instance uses `$TASK_TO_MIGRATE` from user input. Avoid directly embedding unsanitized user input into `sed` commands. Instead, use a safer method for file modification, such as reading the file line by line, performing string replacements in memory, and then writing the modified content back to a temporary file before replacing the original. If `sed` must be used, escape all special characters in the user input that could be interpreted by `sed` (e.g., `&`, `/`, `\`, `|`, ` `). | LLM | scripts/plan.sh:285 | |
| 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/jankutschera/adhd-founder-planner/scripts/plan.sh:6 |
Scan History
Embed Code
[](https://skillshield.io/report/72bc19f5ad2a55fd)
Powered by SkillShield