sdd-explore
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from the project codebase and a skill registry. This presents a surface for indirect prompt injection, where instructions embedded in code or configuration could influence the agent's analysis.
- Ingestion points: Local codebase files and .atl/skill-registry.md.
- Boundary markers: None present; the skill is instructed to read relevant code and follow instructions found in the registry.
- Capability inventory: mem_save, mem_search, file-read operations, and creation of exploration.md.
- Sanitization: No sanitization or validation of external data is specified.
Audit Metadata