team-project-memory

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a high-level router for managing shared project memory without implementing dangerous operations directly.
  • [DATA_EXPOSURE]: The skill includes explicit security invariants that forbid the storage of secrets, personal/customer data, or unredacted confidential logs, which is a defensive best practice.
  • [INDIRECT_PROMPT_INJECTION]: While the skill interacts with shared memory (an external data source), it includes boundary instructions stating that repository-local instructions outrank shared memory and that shared memory should be treated as evidence rather than a source of truth.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:50 PM
Security Audit — agent-trust-hub — team-project-memory