Back to skill

Security audit

Clawddocs

Security checks for vulnerabilities and agentic risk

Overview

This skill mostly looks like a SkillHub documentation helper, but it also asks for command execution and file-writing authority without clear limits.

Review before installing. If you only need SkillHub documentation help, prefer a version that uses read-only documentation retrieval. If installed, run it in a constrained sandbox and require explicit approval before any command execution, file write, API call, or use of environment variables.

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:23
Finding

Excessive Tool Permissions for a Documentation Skill

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 23-26
Vulnerability Type: Least-privilege violation through unnecessary command-execution and file-write capabilities
Risk Level: Medium

Complete Code Snippet:

yaml
tools:
- read
- exec
- write

Technical Analysis

The Skill's declared core purpose is to navigate, retrieve, and summarize SkillHub documentation. Read access and constrained documentation retrieval are sufficient for that functionality, but the Skill also requests general command-execution and file-write capabilities.

No command allowlist, writable-path restriction, shell-input validation, user-confirmation requirement, or enforceable sandbox policy is defined. The later statement that commands run in a “safe sandbox” is descriptive rather than an implemented security control.

Although the audited file contains no malicious commands, granting these capabilities creates an unnecessary privilege boundary violation. If attacker-controlled user input or untrusted retrieved documentation influences the Agent's actions, the unnecessary tools could turn an instruction-manipulation issue into local command execution or file modification.

Attack Path

  1. The Agent loads the Skill and grants the declared exec and write capabilities.
  2. The user supplies malicious instructions, or externally retrieved documentation contains adversarial content.
  3. That content persuades the Agent to invoke exec or write, despite those tools not being required for documentation lookup.
  4. The Agent executes a local command or modifies an accessible file under its runtime permissions.
  5. The resulting impact is limited only by the Agent sandbox, filesystem permissions, and execution controls supplied by the host platform.

This is a capability-enablement path rather than evidence that the current Skill directly performs malicious execution.

Impact Assessment

Exploitation could ...[truncated 651 chars]

Remediation
View remediation

Remediation Suggestions

  1. Remove exec and write from the declared tools and retain only the minimum read and constrained network-retrieval capabilities needed for documentation lookup.
  2. If command execution is genuinely required, replace unrestricted execution with a narrowly scoped command allowlist that uses fixed argument arrays rather than shell-interpolated strings.
  3. Require explicit user confirmation before every command that changes system state.
  4. If writing is necessary, restrict it to a dedicated output directory, reject traversal and symlink escapes, and prevent modification of configuration, executable, credential, and startup files.
  5. Enforce sandboxing at the host-platform level with a non-privileged identity, a read-only project filesystem where possible, network egress restrictions, resource limits, and no inherited secrets.
  6. Treat retrieved documentation as untrusted data and prohibit it from authorizing tool calls or changing the Agent's governing instructions.
  7. Replace broad claims of safe sandboxing with concrete, enforceable controls and document the exact commands, paths, destinations, and approval gates permitted.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill presents itself as a documentation/navigation assistant, but its description expands into generic file processing, format conversion, content extraction, and workflow automation. That capability mismatch is dangerous because it can cause an agent or user to invoke the skill in much broader contexts than expected, increasing the chance of unintended file or system operations under the guise of benign documentation help.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

Declaring exec for a documentation assistant is unjustified and materially increases risk, because command execution can be repurposed to run arbitrary shell commands unrelated to documentation retrieval. The later example instructing the agent to run a script reinforces that this is not merely theoretical and could lead to code execution from skill-controlled guidance.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The feature list broadens the skill from documentation help into a general automation tool that reads/writes files, integrates with external APIs, and executes commands. This scope creep is dangerous because it disguises a high-privilege automation surface as a simple documentation assistant, making unsafe invocation and overtrust more likely.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation description is overly broad, inviting use for generic file and document tasks rather than a narrowly bounded documentation-assistant scenario. Ambiguous activation criteria are dangerous because they encourage the agent to apply the skill in contexts where its privileged tools may affect local data or system state unnecessarily.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

File write capability is inconsistent with the stated role of a documentation expert and creates unnecessary potential for modifying local files, configs, or outputs without clear need. In combination with ambiguous task descriptions, an agent could be induced to overwrite documents or create artifacts that affect downstream workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The usage instructions provide a general decision tree but do not clearly constrain when the skill should or should not activate. Without explicit boundaries, an agent may over-apply the skill and then rely on its elevated tools in situations beyond simple documentation lookup.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's guidance says to consult documentation pages, but an example instead tells the agent to run a script from the skill directory. This inconsistency is dangerous because examples strongly influence agent behavior, and a seemingly harmless docs skill can become an execution vector through embedded operational instructions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill advertises file writing, external API use, and command execution without clear warnings about possible system changes, data exposure, or network impact. This is dangerous because users and agents may interpret the skill as low-risk documentation help while it actually enables actions with meaningful integrity and confidentiality consequences.

Content

No source excerpt is available for this finding.