scale-check
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-provided descriptions and existing files, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The skill accepts a process or system name as input and identifies a mode for updating existing assessment files (e.g.,
path/to/check.md), effectively reading untrusted content into the agent's context. - Boundary markers: There are no explicit instructions to use XML tags, delimiters, or other boundary markers to isolate user-provided content from the agent's core instructions.
- Capability inventory: The skill performs file reading, directory searching, and markdown report generation across all modes (Create, Update, Find).
- Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content found within the subject descriptions or the files being updated.
Audit Metadata