run-product-premortem

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as project requirements, tickets, and customer evidence. This creates a surface for indirect prompt injection where instructions embedded in those documents could influence the agent's behavior. 1. Ingestion points: The skill ingests documents, project details, and linked tickets as specified in SKILL.md. 2. Boundary markers: No delimiters or warnings are specified to differentiate between instructions and untrusted data. 3. Capability inventory: The skill can perform project mutations, though it explicitly requires user approval for such actions. 4. Sanitization: No sanitization or validation of the input data is described.
  • [SAFE]: The skill references external repositories on GitHub for provenance and inspiration. These references point to public repositories on a well-known service and do not involve code execution or automated downloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 03:14 AM