incident-triage

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill instructions proactively mitigate data exposure by directing the agent to ignore secrets and credentials when creating handoff reports.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external incident reports, which constitutes a potential injection surface. The risk remains low because the skill provides no access to shell commands, network operations, or file system modifications.- [NO_CODE]: The skill is composed purely of markdown instructions and does not include any scripts, libraries, or external code dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 06:38 AM
Security Audit — agent-trust-hub — incident-triage