oracle-grill-me
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill directs the agent to explore the filesystem for project facts, which could allow instructions embedded in project files to influence agent behavior. * Ingestion points: Filesystem and environment exploration (SKILL.md). * Boundary markers: Absent. * Capability inventory: Filesystem read access and domain documentation updates (SKILL.md). * Sanitization: No explicit filtering or validation of environmental data is described.
- [SAFE]: The skill's primary function is a structured interview process for domain modeling, with no evidence of malicious obfuscation, persistence, or data exfiltration.
Audit Metadata