grilling
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious code, obfuscation, or unauthorized commands were identified in the skill instructions or configuration.
- [PROMPT_INJECTION]: The skill ingests untrusted data from the user and the local environment, creating a potential indirect prompt injection surface.
- Ingestion points: Processes user-provided plans and ideas, as well as environment facts retrieved from the filesystem and tools via sub-agents (
SKILL.md). - Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined to separate untrusted data from the agent's instructions.
- Capability inventory: The skill is instructed to dispatch sub-agents to access tools and the filesystem to find facts (
SKILL.md). - Sanitization: No explicit sanitization or validation of the ingested data is described.
Audit Metadata