evidence-evaluator-skill
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- SAFE (SAFE): No malicious patterns or security risks detected. The skill consists entirely of logic and evaluation procedures for assessing source credibility.
- NO_CODE (SAFE): The skill does not include any scripts, executable commands, or external dependencies. It functions as a prompt-based instructional set.
- Indirect Prompt Injection (LOW): While the skill processes untrusted external content, the risk is negligible due to the lack of dangerous capabilities.
- Ingestion points: External evidence and sources provided for CRAAP testing (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: No subprocess calls, no network operations, and no file writing; limited to 'Read' access within the agent context.
- Sanitization: Absent.
Audit Metadata