context-builder
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and distill information from potentially untrusted external sources, creating a surface for indirect instructions to influence agent behavior.
- Ingestion points: Reads files from the
reference/andcontext/directories, including meetings, PDFs, and customer documents (SKILL.md, Step 2). - Boundary markers: The instructions do not define clear delimiters or include warnings for the agent to ignore instructions embedded within the source materials.
- Capability inventory: The skill performs file read and write operations to generate
background.mdand update shared context documents (SKILL.md, Steps 3 and 4). - Sanitization: There is no explicit requirement for the agent to sanitize or validate the content of the documents it analyzes.
Audit Metadata