oracle-grill-me
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to ingest data from the local environment and project files to inform its behavior and documentation updates.
- Ingestion points: The agent is directed to explore the filesystem, tools, and existing domain documentation (e.g., CONTEXT.md, ADRs) to gather facts.
- Boundary markers: The prompt does not provide specific delimiters or instructions to ignore potential commands or malicious instructions embedded within the files it reads.
- Capability inventory: The skill uses file-read capabilities to gather context and file-write capabilities to update domain documentation as decisions are finalized.
- Sanitization: There is no mention of sanitizing or validating the content retrieved from the filesystem before processing or including it in documentation.
Audit Metadata