backlog-triage

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources such as bug reports and feature requests. * Ingestion points: Raw requests are ingested verbatim into the triage process as defined in SKILL.md. * Boundary markers: No instructions are provided to the agent to ignore or delimit embedded instructions within the input data. * Capability inventory: The skill's triage outcomes influence prioritization and task generation in downstream tools. * Sanitization: The instructions lack requirements for sanitizing or validating external input.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 04:44 PM