retrospective-workflow

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill includes shell scripts (gather-retro-metrics.sh, init-retrospective.sh, validate-retro.sh) that run local commands like git and npm test. While functional for gathering metrics, this involves executing project-defined test scripts.\n- [PROMPT_INJECTION] (LOW): The facilitation prompt exhibits a surface for indirect prompt injection by ingesting external project data.\n
  • Ingestion points: The agent reads story-tracker.md, delegation/*.md, completion-reports/*.md, and checklists/*.md.\n
  • Boundary markers: Absent; the prompt does not use delimiters or instructions to ignore embedded commands in the source files.\n
  • Capability inventory: The agent can execute local scripts (validate-retro.sh) and write files (retro.md, handoff.yml).\n
  • Sanitization: No escaping or validation of the ingested file content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 04:24 PM