awesome-root-cause
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external data sources which creates a vulnerability to indirect prompt injection.
- Ingestion points: The workflow requires gathering evidence from logs, support tickets, deploy history, and chat transcripts (SKILL.md).
- Boundary markers: There are no instructions for using delimiters or specific 'ignore embedded instructions' warnings to isolate external data from the agent's logic.
- Capability inventory: The skill mentions sub-agents using browsers, language servers, or running tests to collect evidence (SKILL.md).
- Sanitization: No sanitization, escaping, or validation steps are described for the external content before it is processed by the agent.
Audit Metadata