evidence-ledger-research
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected in the skill contents.
- [NO_CODE]: The skill is composed exclusively of natural language instructions and YAML configuration files, with no provided scripts or binaries.
- [PROMPT_INJECTION]: The skill is designed to process untrusted data including documents, URLs, and data tables (ingestion points). While this creates a surface for indirect prompt injection, the skill lacks high-risk capabilities like arbitrary command execution or file system writes, and it employs boundary-like structures via the mandatory 'Evidence Ledger' and 'Source Discipline' instructions to maintain grounding.
Audit Metadata