startup-pipeline
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill logic is focused on workflow management and does not contain patterns for credential theft, unauthorized network access, or code execution.
- [INDIRECT_PROMPT_INJECTION]: The skill maintains context by reading project files from previous sessions, creating a surface for potential injection. 1. Ingestion points: Project directories (e.g., 01-brainstorm). 2. Boundary markers: Absent. 3. Capability inventory: Tools are restricted to WebSearch and Read. 4. Sanitization: None. The risk is minimized by the restricted toolset and is inherent to the skill's primary function.
Audit Metadata