dby-write
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill ingests content from external URLs (via
tool.content.parseDetailmentioned inreferences/materials.md) and fetches past articles/samples via API calls inscripts/write.mjs. - Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted external content from the core writing instructions, increasing the risk of the agent obeying instructions embedded in the source material.
- Capability inventory: The skill has capabilities to write files to the local system (e.g.,
draft.md) and perform network operations to the vendor's API. - Sanitization: There is no evidence of sanitization or filtering of the fetched external text before it is interpolated into the writing context.
Audit Metadata