Trust Assessment
using-hivemind 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 7 findings: 5 critical, 1 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Sensitive environment variable access: $HOME.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 33/100, 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 Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter 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/urcades/hivemind/scripts/common.sh:106 | |
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter 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/urcades/hivemind/scripts/common.sh:112 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/urcades/hivemind/scripts/common.sh:99 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/urcades/hivemind/scripts/common.sh:112 | |
| CRITICAL | Unsecured Remote Script Execution for Updates The skill uses `curl -sSL <URL> | bash` to download and execute an update script from a remote server (`https://hivemind.flowercomputer.com/install`) without any integrity checks (e.g., checksums, GPG signatures) or version pinning. This creates a critical supply chain risk. If the remote server is compromised or the `install` script is maliciously modified, it could lead to arbitrary code execution on the agent's system with the privileges of the agent. Implement a secure update mechanism. This could involve: 1) Using signed packages or scripts. 2) Pinning to specific versions and verifying checksums. 3) Requiring manual review of the update script before execution. 4) Avoiding direct `curl | bash` for unverified remote content. | LLM | scripts/common.sh:99 | |
| HIGH | Arbitrary File Read and Exfiltration via --context-file The `store.sh` script allows users to specify an arbitrary file path using the `--context-file` argument. The content of this file is then read using `cat` and included in the 'context' field of the mindchunk payload, which is subsequently sent to the Hivemind API. This enables a malicious actor (or a compromised agent) to exfiltrate sensitive local files (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, API keys, configuration files) by providing their paths as input to the skill. Restrict the `--context-file` argument to a specific, sandboxed directory or a predefined set of allowed file types. Implement strict content filtering or redaction for sensitive patterns (e.g., private keys, common credential formats) before sending the context to the API. Explicitly warn users about the risks of providing arbitrary file paths. | LLM | scripts/store.sh:70 | |
| 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/urcades/hivemind/scripts/common.sh:7 |
Scan History
Embed Code
[](https://skillshield.io/report/3703cc78503627d1)
Powered by SkillShield