Back to skill

Security audit

corespeed-slide

Security checks for vulnerabilities and agentic risk

Overview

This PowerPoint-generation skill is coherent, but it asks agents to run an unverified remote installer and execute user deck files with broad local file access.

Review before installing. Prefer installing Deno yourself through a trusted package manager, avoid the automatic remote shell installer, and only generate decks from TSX files you wrote or trust. Run the generator with path-scoped read/write permissions where possible.

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 (2)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:15
Finding

Unverified Remote Installer Piped Directly into a Shell

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/generate.ts:33
Finding

Untrusted TypeScript Deck Files Execute with Broad Filesystem Permissions

Content
View full analysis
Remediation
View remediation
,` - `--allow-write=` 3. Resolve and validate the input and output paths before execution, and ensure they fall within explicitly approved directories. 4. Where feasible, replace executable TSX input with a declarative format such as validated JSON that cannot run arbitrary top-level code. 5. If TSX support must remain, execute deck evaluation in an isolated process or container with: - A dedicated temporary working directory. - Read-only access to the selected input. - Write access limited to the designated output directory. - No network, subprocess, environment, or system-directory access. 6. Avoid running the generator under an administrative or otherwise privileged account. 7. Document that checking for `mod.deck` after import is not a security boundary because module code has already executed. ]]>
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

Direct external script fetching and piping to sh is a classic arbitrary code execution pattern. If the remote endpoint, transport, or upstream distribution is compromised, the host running the skill can be fully compromised during installation.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

md
{
              "id": "deno-install",
              "kind": "shell",
              "command": "curl -fsSL https://deno.land/install.sh | sh",
              "bins": ["deno"],
              "label": "Install Deno (https://deno.land)",
            },

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use the skill whenever a user asks to create presentations, slide decks, pitch decks, reports, or any PPTX file, which is broad enough to trigger in many common contexts. Over-broad routing can cause unnecessary activation of a skill that includes code execution and installation behavior, increasing exposure to its riskier capabilities.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill embeds an install step that executes a remotely fetched shell script via curl | sh. That gives arbitrary code execution on the host during skill setup, and while installing Deno is relevant to the skill, using an unchecked remote script is far more privileged and risky than necessary for presentation generation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The installation instructions include curl -fsSL https://deno.land/install.sh | sh without any user-facing warning that it modifies the system and executes remote code. In an agent context, this is dangerous because it can normalize or automate a high-risk action without informed user approval.

Content

No source excerpt is available for this finding.