evaluate-evidence
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content (claims and evidence) provided by users at runtime. This represents a potential surface for indirect prompt injection if the processed data contains malicious instructions. However, the skill lacks dangerous capabilities such as network access, file system writes, or command execution, which significantly mitigates the risk.
- Ingestion points: Processes claims and evidence provided in the user prompt (SKILL.md).
- Boundary markers: None present in the instructions.
- Capability inventory: None. The skill contains only natural language instructions and no tools or scripts.
- Sanitization: No explicit sanitization or filtering of input data is defined.
Audit Metadata