layman
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized persistence mechanisms were detected. The skill follows best practices by explicitly restricting its scope to a read-only transformation task and requiring manual user invocation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content from files and user-provided text, creating an ingestion surface. However, the risk is minimized by the skill's specific purpose of text transformation and lack of destructive capabilities.
- Ingestion points: The skill accepts file paths and inline text as arguments in the Resolving the Input section of SKILL.md.
- Boundary markers: No specific boundary markers or delimiters are defined for the input data to isolate it from instruction context.
- Capability inventory: The skill utilizes the Read tool to ingest file content and the AskUserQuestion tool for interaction.
- Sanitization: The requirement to restate content in plain, jargon-free English acts as a functional behavioral filter on the output.
Audit Metadata