outline-budgeter
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from multiple external files including
outline/outline.yml,queries.md,outline/mapping.tsv,outline/coverage_report.md, andGOAL.mdto update the project outline. - Ingestion points: Data enters the agent context through reading
outline/outline.yml,queries.md,outline/mapping.tsv,outline/coverage_report.md, andGOAL.md. - Boundary markers: The workflow does not specify the use of delimiters or 'ignore embedded instructions' warnings when processing these files.
- Capability inventory: The skill possesses the capability to read from and write to the local file system (specifically
outline/outline.ymlandoutline/OUTLINE_BUDGET_REPORT.md). - Sanitization: There is no evidence of sanitization, validation, or filtering of the content read from the external files before it is used to influence the agent's logic for merging sections.
Audit Metadata