knowledge-priming-refiner

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from repository manifests which creates an indirect prompt injection attack surface.
  • Ingestion points: Scans package.json, Cargo.toml, go.mod, pyproject.toml, and .lattice/config.yaml to inform the agent's behavior during the interview.
  • Boundary markers: Absent; there are no explicit instructions or delimiters used to prevent the agent from following instructions potentially embedded in the repository metadata files.
  • Capability inventory: The skill is capable of reading project files and writing both the knowledge-base document and configuration updates to .lattice/config.yaml.
  • Sanitization: No validation or sanitization of the content from the project manifests is performed before it is used in the conversation context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 11:04 PM
Security Audit — agent-trust-hub — knowledge-priming-refiner