sprint-retrospective

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources that may contain untrusted content.
  • Ingestion points: The instructions in SKILL.md (Steps 1, 3, and 4) direct the agent to gather data from ticket-summary, metrics, customer-feedback, and playtest-feedback.
  • Boundary markers: The skill does not define specific delimiters or "ignore instructions" guardrails when interpolating this external data into the agent's context.
  • Capability inventory: The skill is configured with Bash, Read, Write, Edit, Glob, and Grep tools, which could be leveraged if the agent is successfully manipulated by instructions embedded in the ingested data.
  • Sanitization: No explicit validation or filtering logic for external feedback is provided in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 08:13 AM
Security Audit — agent-trust-hub — sprint-retrospective