authoring-error-tracking-alerts

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill configures alerts that ingest untrusted data from error tracking events, specifically exception names and descriptions. This data is interpolated into notification templates (Slack, Discord, Webhooks) defined in references/block-templates.md. While this is the intended purpose of the skill, it represents a surface where an external attacker who can trigger specific application errors might influence the content of notifications.\n
  • Ingestion points: The templates in references/block-templates.md use event.properties.name and event.properties.description from ingested events.\n
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for the interpolated data within the message blocks.\n
  • Capability inventory: The skill uses posthog:error-tracking-alerts-create in SKILL.md to persist these notification templates, which execute logic (including HogQL expressions) when alerts fire.\n
  • Sanitization: The skill correctly uses encodeURLComponent for URLs as seen in references/event-triggers.md, but does not specify sanitization for plain text or markdown fields in Slack/Discord blocks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:39 AM
Security Audit — agent-trust-hub — authoring-error-tracking-alerts