html-to-interaction-prompts
Warn
Audited by Socket on Aug 25, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill is broadly scoped but coherent for content-capture workflows, with low install-trust and credential risk. The main concern is indirect prompt-injection exposure from analyzing arbitrary live webpages while also being allowed to write files and make git commits.
Confidence: 88%Severity: 56%
Audit Metadata