sprint-brief

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from Jira tickets and Slack, which creates a surface for indirect prompt injection. Evidence: Ingestion points include sprint goals and ticket lists in SKILL.md; no boundary markers or delimiters are present to isolate external data; the skill has no executable capabilities; no sanitization of ticket content is specified.
  • [NO_CODE]: The skill consists entirely of markdown-based instructions and metadata. It does not include any Python or Node.js scripts, reducing the risk of unauthorized command execution or system persistence.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 06:33 AM