humanize-ppt
What this skill does
Presentation system for agent-made PPTs - turns raw material into an AST outline with visual-enhancement decisions, hands a production brief to a downstream renderer, and runs a presentation checkup o
github/nexu-io - Prompt Injection - 84.9k stars
Threat analysis
Skill info
pkg:github/nexu-io/open-design@bf71452?skill=humanize-pptAssessments (2)
Prompt Injection
Prompt Injection via skillspector
references/guizang-production-brief-orchestrator.md
<!-- SLIDES_HERE -->`,
add a `postMessage` bridge, render a fake `outputs/guizang/index.html`.
This broke every time Guizang's template changed:
- `function go(n)` renamed or removed
- `[必填] 替换为 PPT Dangerous Code Execution
Dangerous Code Execution via skillspector
scripts/humanize_ppt_v2.py
subprocess.run(
["git", "clone", "--depth", "1", BEAUTIFUL_REPO_URL, str(cache)],
check=True,
stdout=subprocess.DEVNULL,
stdBadge
Add the Anomity scan badge for humanize-ppt to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of humanize-ppt? Report an issue or request a rescan.
