research
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs an agent to ingest data from external sources including documentation and source code, creating an attack surface for indirect prompt injection.
- Ingestion points: External primary sources like official documentation and source code (SKILL.md).
- Boundary markers: Absent; there are no instructions to differentiate external content from agent instructions.
- Capability inventory: The skill is capable of writing to the local repository filesystem.
- Sanitization: None; the skill does not define methods for filtering or escaping external data before processing.
- [NO_CODE]: The skill consists only of instructional markdown and configuration files, with no executable scripts provided.
Audit Metadata