ln-220-story-coordinator

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external sources.
  • Ingestion points: Reads Epic scope, success criteria, and existing Story content (titles, descriptions, AC) via the Linear API.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested Epic/Story data.
  • Capability inventory: The skill has the ability to write to the project tracking system (update_issue, create_issue) and delegate tasks to other worker skills (ln-221-story-creator, ln-222-story-replanner).
  • Sanitization: The skill implements an output validation step (validateTemplateCompliance) to ensure created Stories meet structure requirements, which provides a partial safety check against corrupted outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 01:53 AM