Book a 30-minute demo →
Skill scan report

espn

View on GitHub
35 Medium This skill contains prompt-injection style instructions. Automated analysis flagged 1 additional risk pattern.

What this skill does

Sports data CLI and agent skill for retrieving live scores, standings, news, and game history from ESPN across multiple sports leagues.

github/mvanhorn - Prompt Injection - 1.9k stars

ThreatsPrompt Injection Excessive Agency

Threat analysis

Prompt Injection1 finding
Excessive Agency1 finding

Skill info

Namemvanhorn/espn
Registrygithub
Version5a78746
PURLpkg:github/mvanhorn/printing-press-library@5a78746?skill=espn
Stars1.9k

Assessments (2)

Prompt Injection1 finding HIGH
HIGH

Prompt Injection via local-llm-review

README.md

The README contains a comment that appears to be a placeholder or anchor for a prompt injection point: <!-- pp-hermes-install-anchor -->. This could be used to inject malicious prompts or instructions
Excessive Agency1 finding MEDIUM
MEDIUM

Excessive Agency via local-llm-review

SKILL.md

The skill's metadata indicates it is allowed to use 'Read Bash' as a tool, which could potentially allow the skill to execute arbitrary shell commands if not properly restricted.

Badge

Add the Anomity scan badge for espn to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/mvanhorn/espn/)
HTML
<a href="https://anomity.ai/skills/github/mvanhorn/espn/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

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 espn? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok