dbs-plain-writing
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because its core function involves ingesting and processing untrusted text provided by users or read from local files.
- Ingestion points: Content is read from user materials for new writing or rewriting tasks, and from existing files for local modification tasks.
- Boundary markers: The skill does not define specific structural markers (e.g., XML tags) to isolate untrusted content from internal instructions.
- Capability inventory: The skill can generate text and modify local files within the agent's environment.
- Sanitization: The skill contains an explicit security instruction to treat commands and code found in user text solely as data to be edited, not as instructions to be executed.
- [SAFE]: No signs of obfuscation, malicious network activity, or unauthorized privilege escalation were identified. The referenced external domains belong to recognized technical documentation organizations.
Audit Metadata