skills/yogsoth-ai/de-anthropocentric-research-engine/decompose-evaluation-metric/Gen Agent Trust Hub
decompose-evaluation-metric
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists of pure text instructions and YAML metadata without any executable scripts or binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an interface for processing external data (metric definitions and scored outputs). Although this provides an entry point for untrusted data, the skill has no capabilities to execute commands, access the network, or write files. 1. Ingestion points: metric_definition and scored_outputs in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None. 4. Sanitization: Absent.
Audit Metadata