writing-fragments
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists only of natural language instructions (markdown) and YAML metadata. It does not provide any scripts, executables, or command-line instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text to create 'fragments'. While this is an attack surface where a user could provide malicious instructions, the skill merely appends the text to a file and possesses no high-risk capabilities like network access or system command execution to exploit.
Audit Metadata