unslop
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow for scanning and rewriting arbitrary text input to remove AI stylistic patterns, which creates a potential surface for indirect prompt injection.
- Ingestion points: The instructions in SKILL.md define a process for the agent to scan and rewrite text provided by users or external sources.
- Boundary markers: The skill does not provide delimiters or instructions for the agent to differentiate between the content to be edited and instructions that might be contained within that content.
- Capability inventory: The skill focus is limited to stylistic text manipulation; there are no tool-based capabilities or system-level access requirements identified in the skill files.
- Sanitization: No input validation or sanitization rules are included to filter or neutralize potentially malicious instructions within the text being processed.
Audit Metadata