text-manipulation-and-converter
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes untrusted text data through various manipulation actions without explicit boundary markers or instructions for the agent to ignore embedded commands.
- Ingestion points: The
textparameter in all 23 actions (e.g.,change-case,normalize-whitespace,sort-lines) serves as an entry point for untrusted data. - Boundary markers: Absent. The skill instructions do not specify the use of delimiters or 'ignore' instructions when passing user-provided content to the tool.
- Capability inventory: The skill allows the agent to execute remote tool calls via the AgentPMT API (MCP/REST), which could be influenced by malicious instructions in the processed text.
- Sanitization: No sanitization or filtering of the input text is described before it is passed to the remote service.
Audit Metadata