concise-copy
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and examples for refining text length and clarity.\n- [NO_CODE]: No scripts, executables, or external dependencies are included in the skill package.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a method for processing and reducing user-provided text or files. While this constitutes a data ingestion surface for potentially malicious instructions, the skill does not possess any tools, network capabilities, or file-system write access that could be exploited.\n
- Ingestion points: Processes user arguments, pasted text, named files, or current selections as defined in
reduce.md.\n - Boundary markers: None specified in the skill instructions.\n
- Capability inventory: None identified; no tools or command execution patterns are present.\n
- Sanitization: None.
Audit Metadata