ingest
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the local file system, creating an attack surface for indirect prompt injection.
- Ingestion points: External data enters the agent context through file reading in the
raw/directory (Step W01 and detailed Step 1). - Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to disregard instructions embedded within the source files being processed.
- Capability inventory: The skill possesses extensive file-writing capabilities across multiple directories, including
wiki/concepts/,wiki/entities/,wiki/sources/, and root wiki files (index.md,log.md), which could be abused if an injection is successful. - Sanitization: There is no evidence of sanitization, escaping, or validation of the ingested content before it is used to generate or update wiki pages.
Audit Metadata