Back to skill

Security audit

Generate Fractional Cfo Firm Client Education Handout

Security checks for vulnerabilities and agentic risk

Overview

This is a simple CFO handout-generation skill, but it requests shell and file-reading access that its workflow does not justify.

Review before installing if your environment gives skills real shell or file-read authority. The artifact does not show exfiltration, persistence, or hidden execution, but a handout generator should not need broad Bash and Read access; prefer a version with those permissions removed or tightly scoped.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:4
Finding

Excessive Shell and Filesystem Permissions for a Content-Generation Skill

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, line 4
Vulnerability Type: Excessive tool permissions and violation of least privilege
Risk Level: Medium

Complete Code Snippet:

yaml
allowed-tools: Bash, Read

Technical Analysis

The skill is intended to create a client education handout, but it grants access to the Bash and Read tools. The documented workflow does not require arbitrary shell command execution or unrestricted local file access. Granting these capabilities expands the skill's authority beyond its stated content-generation purpose and violates the principle of least privilege.

The file does not contain instructions that directly abuse these permissions. Nevertheless, if the skill processes malicious or prompt-injected content, the unnecessary tools could provide an execution channel through which an agent may be induced to run commands or read local files. The actual exploitability depends on how the host enforces tool permissions, user confirmation, path restrictions, command sandboxing, and prompt-injection defenses.

Attack Path

  1. A user or external content source supplies attacker-controlled instructions as part of a handout-generation request.
  2. The injected instructions attempt to redirect the agent from document creation to local system operations.
  3. Because the skill permits Read, the agent may be induced to access local configuration, project files, credentials, or other readable data.
  4. Because the skill permits Bash, the agent may be induced to execute shell commands within the privileges and sandbox boundaries of the hosting process.
  5. Retrieved information could potentially be incorporated into generated output or commands could alter accessible files and processes.

This is a conditional attack path; the audited skill itself contains no malicious command, exfiltration instruction, persistence mechanism, or remote payload retrieval.

Impact Asse

...[truncated 451 chars]

Remediation
View remediation

Remediation Suggestions

  1. Remove Bash and Read from allowed-tools because they are not required by the documented handout-generation workflow.
  2. Permit only narrowly scoped content-generation capabilities, such as the declared chat and image-generation APIs.
  3. If local assets must be read, replace unrestricted Read access with a path-scoped reader limited to a dedicated, non-sensitive input directory.
  4. If command execution later becomes necessary, expose purpose-built operations instead of a general shell. Enforce fixed command templates, argument validation, command allowlists, sandboxing, and explicit user confirmation.
  5. Treat client prompts, uploaded documents, and retrieved content as untrusted data. Prevent instructions embedded in such content from authorizing tool use or changing the skill's security boundaries.
  6. Apply runtime filesystem isolation, least-privileged service accounts, environment-secret filtering, and logging of all sensitive tool invocations.
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The description and 'Use When' guidance say to use the skill for 'client education work' for a fractional CFO firm, but they do not clearly define what kinds of requests are in scope versus out of scope. This broad phrasing could lead to unintended invocation for general finance-content tasks rather than this specific handout-generation use case.

Content

No source excerpt is available for this finding.