scrum
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, such as project specifications, conversational prose, or local file content, to generate structured Scrum artifacts.
- Ingestion points: As described in
SKILL.md, the skill reads material from provided file paths, folders, or conversational prose to create the Product Backlog and Sprint drafts. - Boundary markers: The instructions lack explicit delimiters or specific warnings to ignore potential instructions embedded within the input material, relying on the model's adherence to the provided markdown templates.
- Capability inventory: The skill utilizes file system access to read source materials and write output files to the
scrum/directory within the repository. - Sanitization: There is no evidence of input validation, filtering, or sanitization routines for the processed material in the instructions.
Audit Metadata