coordinate
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow a specific local file (
.agents/workflows/coordinate.md), which constitutes an ingestion surface where malicious instructions could be embedded. - Ingestion points: Reads the
.agents/workflows/coordinate.mdfile referenced inSKILL.md. - Boundary markers: None provided in
SKILL.mdto scope the processing of the workflow file or differentiate between trusted and untrusted instructions. - Capability inventory: No execution or network capabilities (such as subprocess calls or HTTP requests) were detected in the
SKILL.mdfile. - Sanitization: No validation or sanitization of the content from the referenced workflow file is implemented.
Audit Metadata