Trust Assessment
beepctl received a trust score of 76/100, 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, 2 high, 0 medium, and 0 low severity. Key findings include Data Exfiltration via Arbitrary File Attachment, Arbitrary File Write via Download Path.
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 | Data Exfiltration via Arbitrary File Attachment The `beepctl focus <chat-id> -a /path/file` command allows attaching local files to messages. If an attacker can manipulate the LLM to specify an arbitrary file path (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, API keys, configuration files) and send it to an attacker-controlled chat, this could lead to sensitive data exfiltration. The skill's core function is sending messages, making this a direct exploit path if the LLM is compromised. Implement strict validation and user confirmation for any file paths provided to the `-a` argument, especially if they originate from untrusted user input. Consider restricting file access to specific directories or requiring explicit user approval for each file attachment. | LLM | SKILL.md:117 | |
| HIGH | Arbitrary File Write via Download Path The `beepctl download <mxc-url> -o /path` command allows specifying an arbitrary output path for downloaded attachments. While the `mxc-url` is likely internal to Beeper, if an attacker could trick the LLM into downloading a file (even a benign one) and saving it to a sensitive system path (e.g., `/etc/cron.d/malicious`, `~/.bashrc`, or overwriting critical system files), it could lead to denial of service, privilege escalation, or other system compromise. Implement strict validation and user confirmation for the output path (`-o` argument). Restrict downloads to a designated, sandboxed download directory, or require explicit user approval for saving to sensitive locations. | LLM | SKILL.md:136 |
Scan History
Embed Code
[](https://skillshield.io/report/32d7b81559975c0e)
Powered by SkillShield