pythia-spec
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown content designed to guide the agent's decision-making process during software specification gathering.
- [SAFE]: No executable scripts, command-line operations, or network requests are present in the skill definition.
- [SAFE]: The skill uses Vietnamese terminology (e.g., 'căn cứ', 'làm luồng') for context, but these are used as natural language fragments and do not represent obfuscation or hidden commands.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process arbitrary user input, it acts as a safety buffer by requiring the agent to stop and ask for clarification rather than making assumptions that could lead to unintended behavior.
Audit Metadata