sprint-eval

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted input data (sprint plans) which constitutes an indirect prompt injection surface. A maliciously crafted plan could attempt to influence the scoring or behavior of the evaluator agents.
  • Ingestion points: Sprint plans are ingested from file paths or text provided by the user as specified in SKILL.md.
  • Boundary markers: The skill lacks explicit instructions to treat the ingested plan as data only or to ignore any embedded instructions within it.
  • Capability inventory: The skill spawns three specialized agents (EPM, OR, Agentic) to process the input and generate scores and risks.
  • Sanitization: There is no mention of sanitizing or validating the input data before it is read by the evaluator agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 07:44 AM
Security Audit — agent-trust-hub — sprint-eval