conventions
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and manage files within the backlog/ directory, which can act as an ingestion point for untrusted data.
- Ingestion points: Repository files located in backlog/tasks/, backlog/drafts/, and backlog/decisions/ (SKILL.md).
- Boundary markers: None explicitly defined to isolate or sanitize embedded instructions within these files.
- Capability inventory: The skill uses Read, Write, Edit, and Bash tools (SKILL.md).
- Sanitization: There are no documented procedures for sanitizing external content before it is read or processed by the agent.
Audit Metadata