recursive-decision-ledger

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to capture and process external information through 'rollouts' and 'recursive prompting', creating a surface for indirect prompt injection. While the skill includes safety-oriented 'Promotion Rules' to limit destructive operations, it lacks specific boundary markers for untrusted data. * Ingestion points: The 'Rollout Loop' instructions specify capturing new information at time-step zero and loading prior ledgers from files (SKILL.md). * Boundary markers: There are no explicit delimiters or 'ignore embedded instructions' warnings for the data being ingested. * Capability inventory: The skill allows access to Bash, Read, Write, Edit, Grep, and Glob tools, which could be misused if the agent obeys instructions hidden in the processed data. * Sanitization: No specific data validation, filtering, or escaping is mentioned in the logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 03:40 PM
Security Audit — agent-trust-hub — recursive-decision-ledger