adversarial-deliberation
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted claims and criteria as input for its deliberation protocol. 1. Ingestion points: The 'claim_or_candidate' and 'criteria' fields defined in the input contract. 2. Boundary markers: None. The skill relies on structured markdown but lacks explicit delimiters to separate untrusted data from instructions. 3. Capability inventory: None. The skill does not invoke shell commands, file system writes, or network operations. 4. Sanitization: None identified in the provided file.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata, with no accompanying scripts or executable files.
Audit Metadata