ClawHub
Back to skill

Security audit

Api Doc Writer Free

Security checks across malware telemetry and agentic risk

Overview

This API documentation skill is not malicious, but it asks for unnecessary shell command access for a documentation-only workflow.

Review this skill carefully before installing. It appears intended to help write basic API docs, but it grants shell command access that the documented workflow does not need. Avoid providing real API keys or credentials to this skill, and only use it in an environment where you are comfortable with an agent having command execution available.

SkillSpector

By NVIDIA
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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill declares the `exec` tool even though its stated purpose is only to write API documentation. Unnecessary shell execution expands the attack surface: a prompt-injected user request or future skill logic could trigger command execution, potentially exposing local files, environment variables, or credentials such as the documented API key.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The skill lacks clear activation boundaries and scope constraints, which makes it easier for unrelated or adversarial prompts to invoke it. In a skill that also requests `exec`, ambiguous scope increases the chance of the agent applying the skill in unsafe contexts and following broad operational instructions not needed for documentation work.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The capability coverage section is overly broad and vague, extending the skill to loosely related phrases instead of tightly scoped documentation tasks. Overbroad matching increases the risk of accidental activation and prompt-based misuse, especially given the presence of `exec` capability elsewhere in the skill.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill references API keys and includes shell execution capability, but it does not warn about the risk of leaking secrets through commands, logs, or generated outputs. In an agent environment, that omission can lead users or downstream workflows to expose environment variables or run unsafe commands without understanding the privacy and system impact.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.