plan-builder
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data to populate implementation plan templates, which is a surface for indirect prompt injection.\n
- Ingestion points: User input for acceptance criteria and plan titles as specified in
SKILL.md.\n - Boundary markers: The templates in
references/lack specific delimiters or instructions to treat user-provided content as data rather than instructions.\n - Capability inventory: The skill possesses
Read,Write, andEditcapabilities, allowing it to generate and modify files in thedocs/plans/path based on user input.\n - Sanitization: No sanitization or escaping mechanisms for user-provided data are defined in the instructions.
Audit Metadata