Security audit

SendFox

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent SendFox connector, but its setup instructions include unsafe remote installer commands that execute changing network content directly on the user's machine.

Review before installing. Use this skill only with an OOMOL/SendFox account you intend the agent to manage, confirm all write or destructive actions, and avoid the documented curl|bash or irm|iex installer commands unless you have independently verified the installer source and contents. Prefer an official signed or checksum-verified installation path for the oo CLI.

A.I.G

Vulnerability Patterns

Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (3)

T03 · Remote Payload Retrieval and Execution

Error

Location: SKILL.md:68
Finding: Remote Installer Downloaded and Executed Through Bash
Content: View full analysis
Remediation: View remediation

T03 · Remote Payload Retrieval and Execution

Error

Location: SKILL.md:72
Finding: Remote PowerShell Installer Executed In Memory
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:35
Finding: Inline JSON Construction Can Permit Shell Command Injection
Content: View full analysis
" --data '' --json ``` ### Technical Analysis The documented command places JSON inside a single-quoted shell argument. SendFox payloads can contain externally supplied values such as email addresses, names, list data, and custom fields. If an agent constructs this command through direct string substitution, an apostrophe in a value can terminate the shell quote. Subsequent characters may then be interpreted as shell operators or commands rather than JSON data. The document mentions that `--data` accepts `@path/to/file.json`, but it does not require that safer mechanism for untrusted values. Correct JSON serialization alone does not make a value safe for interpolation into shell source because JSON escaping and shell escaping follow different grammars. ### Attack Path 1. An attacker or untrusted data source supplies a SendFox field containing an apostrophe followed by shell syntax. 2. The agent serializes the value as JSON and substitutes the JSON text into the documented command template. 3. The apostrophe terminates the shell's single-quoted argument. 4. Bash parses the remaining attacker-controlled characters as shell syntax. 5. The injected command executes with the local privileges and environment available to the agent. Successful exploitation depends on the command being assembled through unsafe textual interpolation. Using a properly separated process argument array or a JSON file would prevent this path. ### Impact Assessment Successful exploitation could execute arbitrary local commands with the agent's operating-system privileges. The resulting scope may include reading or modifying accessible files, stealing credentials available to the process, making unauthorized ...[truncated 203 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

External Script Fetching

High

Category: Supply Chain
Confidence: 98% confidence
Finding: The skill instructs users to install software via a remote script piped directly into a shell, which executes unreviewed network content immediately. If the install endpoint, transport path, or hosting account is compromised, an attacker can achieve arbitrary code execution on the user's machine.
Content: Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):

bash
curl -fsSL https://cli.oomol.com/install.sh | bash # macOS / Linux

powershell

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest says to use this skill for "ANY SendFox request" and "Whenever a task involves SendFox," which is a very broad activation condition in a manifest file. It does not provide constraints, exclusions, or negative examples to clarify when the skill should not be invoked, increasing the risk of unintended activation for loosely related mentions of SendFox.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.