conversation-json-to-md
Warn
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (MEDIUM): The skill runs
python3 scripts/convert_conversations.py. The logic of this script is not visible and it originates from an untrusted repository (YangsonHung/awesome-agent-skills), which could allow for the execution of malicious commands or unauthorized file access.\n- [PROMPT_INJECTION] (LOW): The skill exhibits an Indirect Prompt Injection surface (Category 8) because it processes untrusted user-provided chat logs.\n - Ingestion points: Input file path provided by the user containing conversation exports.\n
- Boundary markers: No specific delimiters or instructions are provided to the agent to ignore potentially malicious content within the chat logs.\n
- Capability inventory: File system read/write access and subprocess execution via the conversion script.\n
- Sanitization: No sanitization or validation of the input JSON content is specified before the formatting passes are performed.
Audit Metadata