spec-loop-plan-work-breakdown
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves the agent ingesting and processing user-supplied task descriptions, backlog items, and existing task files to generate or revise work breakdown artifacts. This creates an attack surface where malicious instructions embedded within the source task data could influence the agent's behavior during the planning phase.
- Ingestion points: Processes external task files and backlog items specified by the user.
- Boundary markers: None explicitly mentioned in this instruction file to delimit data from instructions.
- Capability inventory: Writing and modifying file-based task artifacts and subtask metadata.
- Sanitization: No evidence of sanitization or schema validation for the input task content.
Audit Metadata