plan-grilling
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze data from external and untrusted sources, which could potentially contain malicious instructions intended to subvert the agent's behavior.
- Ingestion points: The skill reads existing project files, configurations, and history (
SKILL.md), and utilizes theWebSearchtool to gather factual context. - Boundary markers: Absent. The instructions do not define delimiters or provide specific guidance for the agent to ignore instructions embedded within the files or web search results it retrieves.
- Capability inventory: The skill is configured with broad capabilities including
Bash,Write,Edit, andWebSearchtools, allowing it to modify the filesystem and interact with the web based on its analysis. - Sanitization: Absent. There is no evidence of validation or sanitization of content retrieved from the environment before it is interpolated into the agent's context or written back to the filesystem.
Audit Metadata