zenforge-soul
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon external requirements and code snippets, creating a surface where malicious instructions could be embedded in data.
- Ingestion points: Processes 'raw requirements' and 'candidate proposals' as described in the routing logic (SKILL.md).
- Boundary markers: Lacks explicit delimiters or instructions to ignore embedded commands within the external data it processes.
- Capability inventory: Possesses significant capabilities including file system modification (/forge, /tdd), workspace isolation management (/worktree, /forge-isolated), and subagent delegation (/forge-isolated-subagent) as defined in SKILL.md.
- Sanitization: No specific sanitization or validation protocols for external content are defined, relying instead on high-level mindset guidelines.
Audit Metadata