batch-grill-me
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or dangerous commands were detected. The skill is purely instructional and defines a legitimate conversational workflow.\n- [NO_CODE]: The skill does not include any scripts, executable files, or package dependencies.\n- [PROMPT_INJECTION]: The instructions establish a process for ingesting facts from the environment (tools and file system), creating a surface for potential indirect prompt injection. This is a standard risk for interactive agents and is mitigated by the skill's explicit requirement for human confirmation before any actions are taken.\n
- Ingestion points: Facts gathered from tools and the file system, as well as user responses (SKILL.md).\n
- Boundary markers: Absent.\n
- Capability inventory: Mentions the use of tools and file system access for fact-gathering (SKILL.md).\n
- Sanitization: Absent.
Audit Metadata