Security audit

skill-export-audit

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because a scanner flags guidance to run bundled scripts on real inputs without first reviewing or isolating them; the review is partial, so the evidence is incomplete.

Review the skill's instructions carefully before installing. In particular, consider whether you are comfortable with its direction to run scripts on real inputs; avoid exposing sensitive data, credentials, or broad system access to unreviewed scripts. The scan covered the single Markdown component but was marked partial because several local references could not be resolved, so it cannot establish that all related material was assessed.

A.I.G

Vulnerability Patterns

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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
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)

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 85% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.
md
ags complete. Version must be a bump over the server's latest (`clawhub inspect <slug> --json` → `latestVersion`), with a real changelog naming the substantive changes. For a NEW slug, `inspect` errors with "Skill not found or unavailable to this account" — that is confirmation the slug is unused, not a failure; the first version is 1.0.0. ## Phase 5 — Staging hygiene (contamination is the #1 real failure) - Use a FRESH staging directory with a unique name per publish (e.g. `<name>-stage-<version>`). Never reuse a scratch dir: stale content has survived `rm -rf`/`cp -r` and poisoned a real publish. - Copy files explicitly, then `diff -r <in-place> <stage>` MUST be clean before any publish attempt. - Windows: the ClawHub CLI is Node — pass drive-letter paths (`C:/...`); MSYS paths (`/c/...`) fail with exit 1. - `--dry-run` first; check `would-publish`, the **slug** (verify it matches the intended listing — omitted, it derives from the staging folder name), the version, and `fileCount`.

Mandatory execution of bundled scripts against real inputs lacks a warning about potential data and system effects.

Medium

Category: Output Handling
Confidence: 98% confidence
Finding: Phase 2 requires executing every bundled script against real inputs without first reviewing the code, restricting privileges, or isolating execution. Because the skill being audited may be untrusted, this can execute attacker-controlled code with the agent's access to files, credentials, and network resources; the later pre-publish security screen occurs too late to protect this step.
Content: No source excerpt is available for this finding.