how
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted codebase data which represents an attack surface for indirect prompt injection.
- Ingestion points: Data is read from the local workspace using filesystem tools and interpolated into templates in references/explorer-prompt.md and references/explainer-prompt.md.
- Boundary markers: No delimiters or protective instructions are used to isolate the ingested codebase content within the sub-agent prompts.
- Capability inventory: Sub-agents have read-only access to files and the ability to write analysis results to local storage paths as defined in SKILL.md.
- Sanitization: The skill does not perform sanitization or validation of the content retrieved from the codebase before synthesis.
Audit Metadata