skills/yogsoth-ai/de-anthropocentric-research-engine/attach-evidence-to-relation/Gen Agent Trust Hub
attach-evidence-to-relation
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and YAML-based contracts. It does not include any scripts, shell commands, or external resources.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of evidence records, creating a potential surface for indirect prompt injection. 1. Ingestion points: The
evidence_recordsfield in the input contract ofSKILL.md. 2. Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the evidence records. 3. Capability inventory: No dangerous capabilities such as file system writes, network requests, or subprocess execution are present in this skill. 4. Sanitization: No sanitization or filtering logic is specified for the ingested content.
Audit Metadata