amazon-working-backwards
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided product ideas and existing proposal drafts to generate new documentation.
- Ingestion points: The workflow described in
SKILL.mdaccepts user input via chat and reads existing markdown files to refine 5Q answers and PR-FAQ drafts. - Boundary markers: There are no explicit instructions or delimiters mentioned to separate user-provided content from the agent's internal logic, which could allow malicious instructions in the input to be followed.
- Capability inventory: The skill allows the agent to write and edit markdown files (e.g., `YYYY-MM-DD
- [Product Name] 5Q.md
andYYYY-MM-DD - [Product Name] PR-FAQ.md`) based on processed data.
- Sanitization: The skill does not describe any validation, filtering, or escaping of the user-provided text before it is used in the document creation process.
Audit Metadata