dbk-doc-style
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided data, such as project documentation (READMEs, design documents, and PR descriptions), to check for style and grammatical compliance. The instructions explicitly mention a capability to "modify files" when performing style corrections, which establishes an attack surface for indirect prompt injection. A malicious document could contain instructions intended to influence the agent's output or file modification behavior.
- Ingestion points: Processes external user-provided documentation for style checking and editing (defined in SKILL.md).
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are implemented to separate user data from agent instructions.
- Capability inventory: Includes the ability to generate text and modify files based on instructions in the skill context (referenced in the check/edit workflow in SKILL.md).
- Sanitization: No evidence of sanitization or escaping of the ingested document content before processing.
Audit Metadata