espn
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
Threat analysis
Skill info
pkg:github/mvanhorn/printing-press-library@5a78746?skill=espnAssessments (2)
Prompt Injection
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 instructionsExcessive Agency
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.
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.




