scrum-conductor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): Indirect Prompt Injection Surface. The skill is designed to automatically ingest and synthesize untrusted data from external sources, creating a risk that malicious instructions embedded in PRs or chat logs could influence agent behavior.
  • Ingestion points: Git logs, PR descriptions, Slack messages, Microsoft Teams messages, and Jira/Linear tickets as defined in SKILL.md and references/daily-rituals.md.
  • Boundary markers: None identified; there are no specified delimiters to separate untrusted telemetry data from agent system instructions.
  • Capability inventory: The skill has the ability to trigger other agent tools via activate_skill and run local scripts such as scripts/sync-github-to-linear.ts.
  • Sanitization: No mentions of input validation or sanitization are present in the provided protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:31 PM