incident-postmortem-builder
Warn
Audited by Snyk on May 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests timeline data from third-party, user-generated sources — SKILL.md lists "Slack export, PagerDuty incident, or a CSV (timestamp,event,actor)" and build.py's load_timeline opens and parses the provided timeline CSV, so the agent will read and act on untrusted timeline content that can influence metrics, root cause, and action items.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata