backlog-routing-by-topic
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-provided ideas and write them into repository documentation files, creating a potential surface for indirect prompt injection.
- Ingestion points: User-supplied "stray ideas" and meeting log content processed during the conversation (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or boundary markers when interpolating user content into the file entries.
- Capability inventory: The agent is instructed to write to local markdown files (e.g.,
docs/design.md,docs/plan.md,meetings/*.md). - Sanitization: There are no instructions provided to sanitize, escape, or validate the user-provided text before it is committed to the documentation files.
Audit Metadata