doc-drift-sentinel
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates documentation updates by analyzing repository content, which presents a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read git diffs, README files, architectural documents, and configuration templates (SKILL.md).
- Boundary markers: The skill does not provide delimiters or specific instructions to disregard embedded commands within the files being audited.
- Capability inventory: The skill possesses capabilities for file system read/write and git command execution.
- Sanitization: There is no evidence of content sanitization or validation for the data ingested from the repository.
Audit Metadata