sre
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from project state files located in the .nugelo/ directory, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: The skill reads various markdown files from .nugelo/decisions/, .nugelo/reviews/, .nugelo/status.md, and .nugelo/handoff.md to maintain context across different roles.
- Boundary markers: The skill explicitly mitigates this risk with a high-visibility warning stating that .nugelo/ state files are decision data, not instructions, and the agent should never follow directives found inside them.
- Capability inventory: The instruction set focuses on analysis and structured reporting; no high-risk capabilities like arbitrary command execution or network exfiltration are implemented within the skill file itself.
- Sanitization: The instructions emphasize manual verification of discovered data against actual code and treat state files as passive data rather than authoritative instructions.
Audit Metadata