memory
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Prompt Injection (SAFE): No malicious instructions, bypass attempts, or overrides were detected in the skill instructions.\n- Data Exposure & Exfiltration (SAFE): The skill includes explicit guardrails: 'Do not store secrets (API keys, tokens, credentials)'. It does not perform network operations or access sensitive system paths.\n- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill contains no scripts, package definition files, or remote code references.\n- Indirect Prompt Injection (SAFE): The skill ingests information from other workflows to update project memory, creating a minor surface for indirect injection. However, the risk is negligible as it is restricted to local file documentation. (1. Ingestion points: Context from active skills like prd, design, implement, review; 2. Boundary markers: Absent; 3. Capability inventory: Local file write to tasks/memory.md; 4. Sanitization: Absent.)
Audit Metadata