grilling
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions direct the agent to automatically ingest data from the environment (filesystem and tools) to find facts without prompting the user.
- Ingestion points: Local filesystem and tool outputs accessed by sub-agents as described in SKILL.md.
- Boundary markers: The instructions do not define any delimiters or provide warnings to the sub-agents to ignore instructions found within the gathered data.
- Capability inventory: The skill uses sub-agents and tools to explore the environment, which could have broad read access depending on the agent's configuration.
- Sanitization: There is no mention of filtering, escaping, or validating the content found in the environment before it is processed by the agent.
Audit Metadata