Security audit

Slide Maker

Security checks across malware telemetry and agentic risk

Overview

This skill is a broad slide-deck builder with real local and network capabilities, but the inspected behavior is disclosed, purpose-aligned, and scoped to making and reviewing presentations.

Install this as a capable local deck-building tool, not as a passive prompt pack. Use a virtualenv or container if you do not want it installing Python packages into your active interpreter, set SLIDE_MAKER_NO_ENV_CHECK=1 and SLIDE_MAKER_NO_VERSION_CHECK=1 to disable automatic dependency/version checks, and avoid running third-party style.py files without reading them. Be aware that image generation may use Codex session files or a paid OpenAI API path only after the documented billing gate, and that optional taste/profile files persist across decks unless you delete or redirect the registry.

SkillSpector

By NVIDIA

Vulnerability Patterns

Behavioral ASTexec() Call, eval() Call, Dynamic Import
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 (395)

Dangerous chain: exec() wrapping compile

Critical

Category: Dangerous Code Execution
Content: sl = p.slides.add_slide(p.slide_layouts[6]) try: os.chdir(TMP) exec(compile(code, f"<scaffold:{name}>", "exec"), {"dk": dk, "s": sl, "dc": dc}) except Exception as e: bad.append(f"{name}: {type(e).__name__}: {e}") finally:
Confidence: 95% confidence
Finding: A dangerous execution chain combines code execution (exec/eval) with a dynamic source (network, encoded data, dynamic import), creating a high-confidence attack vector.

Ae1

High

Category: analysis-evasion
Content: `references/design-principles.md` for the craft, and treat the actor-critic loop
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `references/design-principles.md` for the craft, and treat the actor-critic loop
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `references/design-principles.md` for the craft, and treat the actor-critic loop
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `references/design-principles.md` for the craft, and treat the actor-critic loop
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `references/design-principles.md` for the craft, and treat the actor-critic loop
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `references/design-principles.md` for the craft, and treat the actor-critic loop
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `references/design-principles.md` for the craft, and treat the actor-critic loop
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `agents/slide-design.md` Design-language output + self-verify (h); the `boldness`/`signature move`
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `agents/slide-design.md` Design-language output + self-verify (h); the `boldness`/`signature move`
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `agents/slide-design.md` Design-language output + self-verify (h); the `boldness`/`signature move`
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `agents/slide-design.md` Design-language output + self-verify (h); the `boldness`/`signature move`
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `agents/slide-design.md` Design-language output + self-verify (h); the `boldness`/`signature move`
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `agents/slide-design.md` Design-language output + self-verify (h); the `boldness`/`signature move`
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `agents/slide-design.md` Design-language output + self-verify (h); the `boldness`/`signature move`
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `agents/slide-design.md` Design-language output + self-verify (h); the `boldness`/`signature move`
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: (`agents/asset-prep.md` — an execution-only worker that runs after the DESIGN plan is approved (Step 2) and makes ZERO
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `python3 scripts/sigs.py text box native_chart takeaway_rail …` prints each signature, its
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `python3 scripts/sigs.py text box native_chart takeaway_rail …` prints each signature, its
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: order; RGBColor vs hex; `picture()` takes the path SECOND). Reading `deckkit.py` one function at a time answers one question per
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: order; RGBColor vs hex; `picture()` takes the path SECOND). Reading `deckkit.py` one function at a time answers one question per
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: order; RGBColor vs hex; `picture()` takes the path SECOND). Reading `deckkit.py` one function at a time answers one question per
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: `python3 scripts/dispatch_brief.py init --deck <dir>`, fill it, then
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: reconstructions, which is what `references/critic-panel.md` asks for and cannot check.
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: reconstructions, which is what `references/critic-panel.md` asks for and cannot check.
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: scripts/archetypes.py:42

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: scripts/assemble.py:84

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: scripts/codex_delivery_gate.py:544

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: scripts/palette_audit.py:86

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: scripts/register_surface.py:970

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: scripts/slide_index.py:41

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: tests/test_codex_delivery_gate.py:57

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: tests/test_codex_visual_contract.py:20

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: tests/test_decodability.py:256

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: tests/test_step1_artifacts.py:357