flow-triage
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional text providing a framework for incident triage. It does not include scripts, command execution, or network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting and analyzing externally-provided incident reports, which is a potential injection surface. Ingestion points: Processes 'noisy reports' and 'observed behavior' (SKILL.md). Boundary markers: None defined. Capability inventory: None within this skill; the instructions specify routing to other 'flow' skills for action. Sanitization: Not specified.
Audit Metadata